UNITING THE TRIBES: USING TEXT FOR MARKETING INSIGHT

Jonah Berger

Ashlee Humphreys

Stephan Ludwig

Wendy W. Moe

Oded Netzer

David A. Schweidel

UNITING THE TRIBES: USING TEXT FOR MARKETING INSIGHT

ABSTRACT

Words are part of almost every marketplace interaction. Online reviews, customer service calls,

press releases, marketing communications, and other interactions create a wealth of textual data.

But how can marketers best use such data? This article provides an overview of automated

textual analysis and details how it can be used to generate marketing insights. We discuss how

text reflects qualities of the text producer (and context in which the text was produced) and

impacts the audience or text recipient. Next, we discuss how text can be a powerful tool both for

prediction and for understanding (i.e., insights). Then, we overview methodologies and metrics

used in text analysis, providing a set of guidelines and procedures. Further, we highlight some

common metrics and challenges and discuss how researchers can address issues of internal and

external validity. Finally, we conclude with a discussion of potential areas for future work.

Along the way, we note how textual analysis can unite the tribes of marketing. While most

marketing problems are interdisciplinary, the field is often fragmented. By involving skills and

ideas from each of the subareas of marketing, text analysis has the potential to help unite the

field with a common set of tools and approaches.

Keywords: text analysis, natural language processing, text mining, machine learning,

computational linguistics, marketing insight, interdisciplinary

The digitization of information has made a wealth of textual data readily available.

Consumers write online reviews, answer open-ended survey questions, and call customer service

representatives (the content of which can be transcribed). Firms write ads, email frequently,

publish annual reports, and issue press releases. Newspapers write articles, movies have scripts,

and songs have lyrics. By some estimates, 80-95% of all business data is unstructured, and most

of that unstructured data is text (Gandomi and Haider 2015).

Such data has the potential to shed light on consumer, firm, and market behavior, as well

as society more generally. But by itself, all this data is just that. Data. For data to be useful,

researchers have to be able to extract underlying insight—to measure, track, understand, and

interpret the causes and consequences of marketplace behavior.

This is where the value of automated textual analysis comes in. Automated textual

analysis

is a computer-assisted methodology that allows researchers to rid themselves of

measurement straitjackets, such as scales and scripted questions, and to quantify the information

contained in textual data as it naturally occurs. Given these benefits, the question is no longer

whether or not to use automated text analysis, but how these tools can best be used to answer a

range of interesting questions.

This article provides an overview of the use of automated text analysis for marketing

insight. Methodologically, text analysis approaches can describe “what” is being said and “how”

it is said, using both qualitative and quantitative inquiries with various degrees of human

involvement. These approaches consider individual words and expressions, their linguistic

relationships within a document (within-text interdependencies) and across documents (across-

Computer-aided approaches to text analysis in marketing research are generally, almost interchangeably, referred to

as computer-aided text analysis (Pollach 2012), text mining (Netzer et al. 2012), automated text analysis

(Humphreys and Wang 2017) or computer-aided content analysis (Dowling and Kabanoff 1996).

text interdependencies) as well as the more general topics discussed in the text. Techniques range

from computerized word-counting and applying dictionaries to supervised or automated machine

learning that help deduce psychometric and substantive properties of text.

Within this emerging domain, we aim to make four main contributions. First, we

illustrate how contextual factors between producers and receivers shape both the creation and

interpretation of text. Second, we provide a how-to guide for those new to text analysis, detailing

the main tools, pitfalls, and challenges that researchers may encounter. Third, we offer a set of

expansive research propositions pertaining to using text as means to understand meaning making

in markets with a focus on how customers, firms, and societies construe or comprehend

marketplace interactions, relationships, and themselves. While previous treatments of text

analysis have looked specifically at consumer text (Humphreys and Wang 2017), social media

communication (Kern et al. 2016), or psychological processes (Tausczik and Pennebaker 2010),

we aim to provide a framework for incorporating text into marketing research at the individual,

firm, market and societal levels. By necessity, our approach includes a wide-ranging set of

textual data sources (e.g., user-generated content, annual reports, cultural artifacts, government

text, etc.).

Fourth, and most importantly, we discuss how text analysis can help unite the tribes. As a

field, part of marketing’s value is its interdisciplinary nature. Unlike core disciplines such as

psychology, sociology, or economics, the marketing discipline is a big tent that allows

researchers from different traditions and research philosophies (e.g., quantitative modeling,

consumer behavior, strategy, and consumer culture theory) to come together to study related

questions (Moorman et al. 2019a,b). In reality, however, the field often feels fragmented. Rather

than different rowers all simultaneously pulling together, it often feels more like separate tribes,

each independently going off in separate directions. While everyone is theoretically working

towards similar goals, there tends to be more communication within groups than between them.

Different groups often speak different languages (e.g., psychology, sociology, anthropology,

statistics, economics, or organizational behavior) and use different tools making it increasingly

difficult to have a common conversation. But text analysis can unite the tribes. Not only does it

involve skills and ideas from each of these areas, doing it well requires such integration;

Borrowing ideas, concepts, approaches, and methods from each tribe, and incorporating them to

achieve insight. In so doing, the approach also adds value to each of the tribes in ways that might

not otherwise be possible.

We start by discussing the world of text that is out there, and the roles of text producers

and text consumers. Next, we discuss two distinctions that are useful when thinking about how

text can be used—whether text reflects or impacts (i.e., says something about the producer or

have a downstream impact on something else) and whether text is used for prediction or

understanding (i.e., predicting something or understanding what caused something). Then, we

explain how text may be used to unite the tribes of marketing, provide an overview of text

analysis tools and methodology, and discuss key questions and measures of validity. Finally, we

close with a future research agenda.

TEXT REFLECTS (PRODUCERS) AND TEXT IMPACTS (RECEIVERS)

Communication is an integral part of marketing. Not only do firms communicate with

customers, but customers communicate with firms and one another. Firms also communicate

with investors, society (through newspapers and movies) communicates ideas and values, and the

list goes on and on. These communications generate text or can be transcribed into text.

A simple way to organize the world of textual data is to think about producers and

receivers—the person or organization that creates the text and the person or organization who

consumes the text. While there are certainly other parties that could be listed, as noted above,

some of the main producers and receivers are consumers, firms, investors, and society at large.

Consumers write online reviews that are read by other consumers, firms create annual reports

that are read by investors, and cultural producers represent societal meanings through the

creation of books, movies, and other digital or physical artifacts that are consumed by individuals

or organizations.

As can be seen in Table 1, the preponderance of existing work has focused on consumers,

either as the producers of text, receivers of text, or both. Part of this is due to data availability.

The wealth of digital data available, particularly from social media, has made it an easier area to

study. But there is much work to be done involving offline data, as well as examining some of

the less studied areas of this grid. We discuss this more deeply in the general discussion.

[Insert Table 1 here]

Consistent with this distinction between text producer and text receiver, researchers may

choose to study how text reflects or how it impacts. Specifically, text reflects information about,

and thus can be used to gain insight into, the text producer, or one can study how text impacts

the text receiver.

Text as a Reflection of the Producer

Text reflects and indicates something about the text producer, i.e., the person,

organization, or context that created it. Customers, firms and organizations use language to

express themselves or achieve desired goals, and as a result, text signals information about the

actors, organization, or society that created it and the contexts in which it was created. Like an

anthropologist piecing together pottery shards to learn about a distant civilization, text provides a

window into its producers.

Take a social media post where someone talks about what they did that weekend. The

text that person produces provides insight into several facets. First, it provides insight into the

individual themselves. Are they introverted or extraverted? Neurotic or conscientious? It sheds

light on who they are in general (i.e., stable traits or customer segments, Moon and Kamakura

2017) as well as how they may be feeling or what they may be thinking at the moment (i.e.,

states). In a sense, language can be seen as a fingerprint or signature (Pennebaker 2011). Just like

brush strokes or painting style can be used to determine who painted a particular painting,

researchers use words and linguistic style to make inferences about whether or not a play was

written by Shakespeare, or if a person is depressed (Rude et al. 2004) or being deceitful (Ludwig

et al. 2016). The same is true for groups, organizations, or institutions. Language reflects

something about who they are and thus provides insight into what they might do in the future.

Second, text can provide insight into a person’s attitudes towards or relationships with

other attitude objects. Whether that person liked a movie or hated a hotel stay, for example, or

whether they are friends with someone or enemies with someone else. Language used in loan

applications provides insight into whether people will default (Netzer et al. 2019), language used

in reviews can provide insight into whether they are fake (Anderson and Simester 2014; Ott et al.

2012; Hancock et al. 2007), and language used by political candidates could be used to study

how they might govern in the future.

These same approaches can also be used to understand leaders, organizations, or cultural

elites through the text they produce. For example, the words a leader uses reflects who they are

as an individual, their leadership style, and their attitudes towards various stakeholders. The

language used in ads, on websites, or by customer service agents reflects information about the

company those pieces of text represent. Aspects like brand personality (Opoku et al. 2006), how

much they are thinking about their customers (Packard and Berger 2019), managers’ orientation

toward end users (Molner et al. 2018), market intelligence dissemination practices (Gebhardt et

al. 2019) or even their financial performance or how well they are likely to perform in the future

(Loughran and McDonald 2016) can be understood through text.

But beyond single individuals or organizations, text can also be aggregated across

creators to study larger social groups or institutions. Given that texts reflect information about

the people or organizations that created them, grouping people or organizations together based

on shared characteristics can provide insight into the nature of such groups and differences

between them. Analyzing blog posts, for example, can shed light on how older and younger

people see happiness differently (e.g., as excitement vs. peacefulness, Mogilner et al. 2010).

Comparing newspaper articles and press releases about different business sectors, text can be

used to understand the creation and spread of globalization discourse from the finance sector in

the 1980s and then spread to other sectors in the early and mid-90s (Fiss and Hirsch 2005).

Customers’ language use further gives insight into the consumer sentiment in online brand

communities (Homburg et al. 2015).

More broadly, because texts are shaped by the contexts (e.g., devices, cultures, or time-

periods) in which they were produced, texts also reflect information about these contexts. In the

case of culture, American culture values high arousal positive affective states more than East

Asian culture (Tsai 2007), and these differences may show up in the language these different

groups use. Similarly, while members of individualist cultures may tend to use first-person

pronouns (e.g., “I”), members of collectivist cultures may tend to use a greater proportion of

third-person pronoun (e.g., “we”)

Looking across time, researchers were able to examine whether the national mood

changed after 9/11 by studying linguistic markers of psychological change in online diaries

(Cohn et al. 2004). The language used in news articles, songs, and public discourse reflect

societal attitudes and norms, and thus analyzing changes over time can provide insight into

aspects such as attitudes towards women and minorities (Garg et al. 2018; Boghrati and Berger

2019) or certain industries (Humphreys 2010). Journal articles provide a window into the

evolution of topics within academia (Hill and Carley 1999). Books and movies serve as similar

cultural barometers, and could be used to shed light on everything from cultural differences in

customs to changes in values over time.

Consequently, text analysis can provide insights that may not be easily (or cost

effectively) obtainable through other methods. Companies and organizations can use social

listening (e.g., online reviews and blog posts) to understand whether consumers like a new

product, how customers feel about their brand, what attributes are relevant for decision making,

or what other brands fall in the same consideration set (Lee and Bradlow 2011; Netzer et al.

2012). Regulatory agencies can determine adverse reactions to pharmaceutical drugs (Feldman et

al. 2015; Netzer et al. 2012), public health officials can gauge how bad the flu will be this year

and where it will hit the hardest (Alessa and Faezipour 2018), and investors can try to predict the

performance of the stock market (Bollen et al. 2011; Tirunillai and Tellis 2012).

Text’s Impact on the Receivers

In addition to reflecting information about the people, organizations, or society that

created it, text also impacts or shapes the attitudes, behavior, and choices of the audience that

consumes it.

Take the language used by a customer service agent. While that language certainly

reflects something about that agent (e.g., their personality or how they are feeling that day), how

they feel towards the customer, and what type of brand they represent, that language also impacts

the customer who receives it (Packard et al. 2018; Packard and Berger 2019). It can change

customer attitudes towards the brand, influence future purchase, or affect whether they talk about

the interaction with their friends. In that sense, language has a meaningful and measurable

impact on the world. It has consequences.

This can be seen in a myriad of different contexts. Ad copy shapes customers’ purchase

behaviour (Stewart and Furse 1986), newspaper language changes customers’ attitudes

(Humphreys and LaTour 2013), trade publications and consumer magazines shift product

category perceptions (e.g., Rosa et al. 1999), movie scripts shape audience reactions (Eliashberg

et al. 2014; Reagan et al. 2016; Berger et al. 2019a), and song lyrics shape song market success

(Berger and Packard 2018; Packard and Berger 2019). The language used in political debates

shapes what topics get attention (Berman et al. 2019), the language used in conversation shapes

interpersonal attitudes (Huang et al. 2017), and the language used in news articles shapes

whether people read (Berger et al. 2019b) or share them (Berger and Milkman 2012).

Firms’ language choice has impact as well. For example, nuances in language choices by

firms when responding to customer criticism online directly impacts consumers and thus the

firms’ success in containing social media firestorms (Herhausen et al. 2019). Language used in

YouTube ads is correlated with their virality (Tellis et al. 2019). Shareholder complaints on

nonfinancial concerns and topics that receive high media attention substantially increase firms’

advertising investments (Wies et al. 2019).

The Two Roles of Text in Marketing Research

Note that while the distinction between text reflecting and impacting is a useful one, it is

not an either/or. Text almost always simultaneously reflects and impacts. Text always reflects

information about the actor or actors that created it. As long as some audience consumes that

text, it also impacts that audience.

Despite this relationship, researchers studying reflection versus impact tend to use text

differently. Research that examines what text reflects often treats it as a dependent variable.

Examining how the text someone creates relates to their personality, the social groups they

belong to, or the time period or culture in which it was created.

Research that examines how text impacts often treats it as an independent variable,

examining if and how text shapes outcomes like purchase, sharing, or engagement. In this

framework, textual elements are linked with outcomes that are thought to be theoretical

consequences of the textual components or some latent variable that they are thought to

represent.

Contextual Influences on Text

Importantly, text is also shaped by contextual factors, so to better understand its meaning

and impact, it is important to understand the broader situation in which it was produced. Context

can affect content in three ways: through technical constraints and social norms of the genre,

through shared knowledge specific to the speaker and receiver, and through prior history.

First, different types of texts are influenced by formal and informal rules and norms that

shape the content and expectations about the message. For example, newspaper genres such as

opinion pieces or feature stories will contain less “objective” point of view than traditional

reporting (Ljung 2000). Hotel comment cards and other feedback is usually dominated by more

extreme opinions. On SnapChat and other social media platforms, messages are relatively recent,

short and often ephemeral. In contrast, online reviews can be longer and are often archived

dating back several years. Synchronic text exchanges, where two individuals interactively

communicate in real time may be more informal and contain dialogue of short statements and

phatic responses (i.e., communication such as “Hi” which serves a social function) that indicate

affiliation rather than semantic content (Kulkarni 2014). Some genres (e.g., social media) are

explicitly public, while on others, such as blogs, information that is more private may be

conveyed.

Text is also shaped by technological constraints (e.g., the ability to like or share) and

physical constraints (e.g., character length limitations). Tweets, for example, necessarily have

288 characters or less, which may shape the ways in which they are used to communicate.

Mobile phones have constraints on typing and may shape the text that people produce on them

(Melumad et al. 2019; Ransbotham et al. 2019).

Second, the relationship between the text producer and consumer may affect what is said

(or more often unsaid). If the producer and consumer know each other well, text may be

relatively informal (Goffman 1959) and lack explicit information that a third party would need to

make sense of the conversation (e.g. events in the past, known likes or dislikes). If both have an

understanding of the goal of the communication (e.g. that the speaker wants to persuade the

receiver), this may shape the content, but be less explicit.

These factors are important to understand when interpreting the content of the text itself.

Content has been shown to be shaped by the creator’s intended audience (Vosoughi et al. 2018),

and anticipated effects on the receiver (Barasch and Berger 2014). Similarly, what consumers

share with their best friend may be different (e.g., less impacted by self-presentational

motivations) then what they post online for everyone to see.

Firms’ annual reports may be

shaped by the goals of appearing favorably to the market. What people say on a customer service

call may be driven by the goal of getting monetary compensation. Consumer protests online are

meant to inspire change, not merely inform others.

Finally, history may affect the content of the text. In message boards, prior posts may

shape future posts; if someone raised a point in a previous post, the respondent will most likely

refer to the point in future posts. If retweets are included in an analysis, this will bias content

toward most circulated posts. More broadly, media frames such as #metoo or #blacklivesmatter

might make some concepts or facts more accessible to speakers and therefore more likely to

emerge in text, even if seemingly unrelated (McCombs and Shaw 1972; Xiong et al. 2019).

USING TEXT FOR PREDICTION VERSUS UNDERSTANDING

Beyond reflecting information about the text creator, and shaping outcomes for the text

recipient, another useful distinction is whether text is used for prediction or understanding.

Prediction

Some text research is predominantly interested in prediction. Which customer is most

likely to default on their loan (Netzer et al. 2019)? Which movie will sell the most tickets

(Eliashberg et al. 2014)? How will the stock market perform (Bollen et al. 2011; Tirunillai and

Note that intermediaries can amplify (e.g., retweet) an original message and may have different motivations than the

text producer.

Tellis 2012)? Whether focusing on individual, firm, or market level outcomes, the goal is to

predict with the highest degree of accuracy. Such work often takes a large number of textual

features, and uses machine learning or other methods to combine these features in a way that

achieves the best prediction. It cares less about any individual feature and more about how the

set of observable features can be combined to predict an outcome.

The main difficulty involved with using text for predictions is that text often generates

hundreds and often thousands of features (words) that are all potential predictors for the outcome

of interest. In some cases, the number of predictors is larger than the number of observations,

making traditional statistical predictive models largely impractical. To address this issue,

researchers often resort to machine learning-type methods, but over-fitting needs to be carefully

considered. Additionally, inference with respect to the role of each word in the prediction can be

difficult. Methods such as feature importance weighing can help extract some inference from

these predictive models.

Understanding

Other research is predominantly interested in using text for understanding. Why does

some online content get shared, songs become popular, or brands engender greater loyalty? How

do cultural attitudes or business practices change? Whether focusing on individual, firm, or

market level outcomes, the goal is to understand why or how something occurred. Such work

often involves examining only one, or a small number of textual features or aspects, that link to

underlying psychological or sociological processes. To understand which features in particular

are driving outcomes and why.

One challenge with using textual data for understanding is drawing causal inferences

from observational data. Consequently, work in this area may augment field data with

experiments to allow key independent variables to be manipulated. Another challenge is

interpreting relationships with textual features (we discuss this further in the closing section).

Songs that use more second person pronouns are more popular (Packard and Berger 2019), for

example, but that doesn’t necessarily say why. Second person pronouns may indicate several

things. Consequently, deeper theorizing, examination of links observed in prior research, or

further empirical is often needed.

Note that research that can use either a prediction or understanding lens to study either

what text reflects or what it impacts. On the prediction side, researchers interested in what text

reflects could use it to predict states or traits of the text creator like customer satisfaction,

likelihood of churn, or brand personality. Researchers interested in the impact of text could

predict how text will shape outcomes such as reading behavior, sharing, or purchase among

consumers of that text.

On the understanding side, someone interested in what text reflects could use it to

understand why people might use certain types of personal pronouns when they are depressed or

why customers might use certain types of emotional language when they are talking to customer

service. Someone interested in the impact of text could use it to understand why text that evokes

different emotions might be more likely to be read or shared.

Further, while most research tends to focus on either prediction or understanding, some

work integrates both aspects. Netzer et al. (2019), for example, both uses a range of available

textual features to predict whether a given person will default on a loan, as well as analysing the

specific language people that tend to default are more likely to use (e.g., language used by liars).

UNITING THE TRIBES OF MARKETING

Regardless of whether someone focuses on what text reflects or impacts and on

prediction or understanding, doing text analysis well requires integrating skills, techniques, and

substantive knowledge from different areas of marketing. Further, textual analysis opens up a

wealth of opportunity for each of these areas as well.

Take consumer behavior. While hypothetical scenarios can be useful, behavioral

economics has recently gotten credit for many applications of social or cognitive psychology

because they have demonstrated phenomena in the field. Given concerns about replication,

researchers have started to look for new tools that enable them to ensure truth and increase

relevance to external audiences. Previously, use of secondary data was often limited because it

addressed the “what” but not the “why.” What people bought or did, but researchers not why

they did so. But text can provide a window into the underlying process. Online reviews, for

example, can be used to understand why someone bought one thing rather than another. Blog

posts can help understand consideration sets (Lee and Bradlow 2011; Netzer et al. 2012) and the

customer journey (Li and Du 2011). Text even helps address the age-old issue of telling more

than we can know (Nisbett and Wilson 1977). While people may not always know why they did

something, their language often provides traces (Pennebaker 2011), even beyond what they can

consciously articulate.

This richness is attractive to more than just behavioral researchers. Text opens a large-

scale window into the world of why in the field and does so in a scalable manner. Quantitative

modelers are always looking for new data sources and tools to explain and predict behavior.

Unstructured data provides a rich set of predictors that are often readily available, at large scale,

and could be combined with structured measures as either dependent variables or independent

variables. Text, through product reviews, user-driven social media activity, and firm-driven

marketing efforts provide data in real-time that can shed light on consumer needs/preferences.

This offers an alternative or supplement to traditional marketing research tools. In many cases,

text can be tied back to an individual, allowing distinction between individual differences and

dynamics. It also offers a playground where new methodologies from other disciplines can be

applied (e.g., deep learning; LeCun et al. 2015; Liu et al. 2019).

Marketing strategy researchers want logics by which business can achieve its marketing

objectives and to better understand what impacts organizational success. A primary challenge to

these researchers is to obtain reliable and generalizable survey or field data about factors that lie

deep in the firm’s culture and structure or that are housed in the mental models and beliefs of

marketing leaders and employees. Text analysis offers an objective and systematic solution to

assess constructs in naturally-occurring data (e.g., letters to shareholders, press releases, patent

text, marketing messages, and conference calls with analysts) that may be more valid. Likewise,

marketing strategy scholars often struggle with valid measures of a firm’s marketing assets, and

text may be a useful tool to understand the nature of customer, partner, and employee

relationships and the strength of brand sentiments. For example, Kübler et al. (2017) use

dictionaries and support vector machine methods to extract sentiment and relate it to consumer

mindset metrics.

Scholars who draw from anthropology and sociology have long examined text through

qualitative interpretation and content analysis. Consumer culture theory (CCT)-oriented

marketing researchers are primarily interested in understanding underlying meanings, norms, and

values of consumers, firms, and markets in the marketplace. Text analysis provides a tool for

quantifying qualitative information to measure changes over time or make comparisons between

groups. Sociological and anthropological researchers can use automated text analysis to identify

important words, locate themes, link them to text segments, and examine common expressions in

their context. For example, to understand consumer taste practices, Arsel and Bean (2012) use

text analysis to first identify how consumers talk about different taste objects, doings, and

meanings in their textual dataset (comments on a website/blog) before analyzing the relationship

between these elements using interview data.

For marketing practitioners, textual analysis unlocks the value of unstructured data and

offers a hybrid between qualitative and quantitative marketing research. Like qualitative research

it’s rich, exploratory and can answer the “why”, but like quantitative research it benefits from

scalability, which often permits modeling and statistical testing. Textual analysis allows

researchers to explore open-ended questions for which they do not know the range of possible

answers a-priori. With text you can answer questions that you didn’t ask. Or didn’t know what

the right outcome measure would be. Rather than forcing a certain scale or set of outcomes from

which to select on participants, for example, marketing researchers can instead ask them broad

questions such as why they like or dislike something and then use topic modeling tools such as

LDA (which will be explained in detail later) to discover the key underlying themes.

Importantly, while text analysis offers opportunities for a variety of research traditions,

such opportunities are more likely to be realized when researchers work across traditional

subgroups. That is, the benefits of computer-aided text analysis are best realized if we include

both quantitative, positivist analyses of content and qualitative, interpretive analyses of

discourse. Quantitative researchers, for example, have the skills to build the right statistical

models, but can benefit from behavioral and qualitative researcher’s ability to link words to

underlying psychological or social processes as well as marketing strategy researcher’s

understanding of organizational and marketing activities driving firm performance. And this is

true across all of the groups.

Thus to really extract insights from textual data, research teams must have the

interpretative skills to understand the meaning of words, the behavioral skills to link them to

underlying psychological processes, the quantitative skills to build the right statistical models,

and the strategy skills to understand what these findings mean for firm actions and outcomes. We

outline some potential areas for fruitful collaboration in the General Discussion.

TEXT ANALYSIS TOOLS, METHODS, AND METRICS

Given the recent work using text analysis to derive marketing insight, some researchers

may wonder where to start. This section reviews methodologies often used in text-based

research. These include techniques needed to convert text into constructs in the research process

as well as procedures needed to incorporate extracted textual information into subsequent

modeling and analyses. The objective of this section is not to provide a comprehensive tutorial,

but rather to expose the reader to available techniques, discuss when different methods are

appropriate, and highlight some of the key considerations in applying each method.

The process of text analysis involves several steps: (1) data pre-processing, (2) text

analysis of the resulting data, (3) converting the text into quantifiable measures, and (4) assessing

the validity of the extracted text and measures. Each of these steps may vary depending on the

research objective. Table 2 provides a summary of the different steps involved in the text

analysis process from pre-processing to commonly used tools and measures and validation

approaches. Table 2 can serve as a starter kit for those taking their first steps with text analysis.

[Insert Table 2 here]

Data Pre-Processing

Text is often unstructured and “messy,” so before any formal analyses can take place,

researchers must first pre-process the text itself. This step provides structure and consistency so

that the text can be used systematically in the scientific process. Common software tools for text

analysis include Python (https://www.nltk.org/) and R (https://cran.r-

project.org/web/packages/quanteda/quanteda.pdf, https://quanteda.io/). For both software

platforms, a set of relatively easy-to-use tools have been developed to perform most of the data

pre-processing steps. Some programs such as LIWC (Tausczik and Pennebaker 2010) and

Wordstat (Peladeu 2016) require minimal pre-processing. We detail the data pre-processing steps

next (see Table 3 for a summary of the steps).

[Insert Table 3 here]

Data acquisition. Data acquisition can be well defined if the researcher is provided with

a set of documents (e.g., e-mails, quarterly reports or a dataset of product reviews) or more open-

ended if the researcher is using a Web scraper (e.g., BeautifulSoup) that searches the Web for

instances of a particular topic or a specific product. When scraping text from public sources,

researchers should abide to the legal guidelines for using the data for academic or commercial

purposes.

Tokenization. This is the process of breaking the text into units (often words and

sentences). When tokenizing, the researcher needs to determine the delimiters that define a token

(space, period, semi-colon, etc). If, for example, a space or a period is used to determine a word,

it may produce some non-sensical tokens. For example, “the U.S.” may be broken to the tokens

“the”, “U”, and “S”. Most text mining software have smart tokenization procedures to alleviate

such common problems, but the researcher should pay close attention to instances that are

specific to the textual corpora. For cases that include paragraphs or threads, depending on the

research objective, the researcher may wish to tokenize these larger units of text as well.

Cleaning. HTML tags and non-textual information, such as images, are cleaned or

removed from the dataset. The cleaning needs may depend on the format in which the data was

provided/extracted. Data extracted from the Web often requires heavier cleaning due to the

presence of HTML tags. Depending on the purpose of the analysis, images and other non-textual

information may be retained. Contractions such as “isn’t” and “can’t” need to be expanded at this

step. In this step, researchers should also be mindful of and remove phrases automatically

generated by computers that may occur within the text (e.g., “html”).

Removing stop words. Stop words are common words and pronouns such as “a” and

“the” that appear in most documents but often provide no significant meaning. Common text

mining tools (e.g., the tm, quanteda, tidytext, and tokenizers package in R or the NLTK package

in Python, exclusion words in WordStat) have a pre-defined list of such stop words that can be

amended by the researcher. It is advisable to add common words that are specific to the specific

domain (e.g., “Amazon” in a corpora of Amazon reviews) to this list. Depending on the research

objective, stop words can sometimes be very meaningful and researchers may wish to retain

them for their analysis. For example, if the researcher is interested in extracting not only the

content of the text but also writing style (e.g., Packard et al. 2018), stop words can be very

informative (Pennebaker 2011).

Spelling. Most text mining packages have pre-packaged spellers that can help correct

spelling mistakes (e.g., the Enchant speller). In using these spellers, the researcher should be

aware of language that is specific to the domain and may not appear in the speller, or even worse,

be incorrectly “fixed” by the speller. Also, for some analyses the researcher may want to record

the number of spelling mistakes as an additional textual measure reflecting important states or

traits of the communicator (e.g., Netzer et al. 2019).

Stemming and lemmatization. Stemming is the process of reducing the words into their

word stem. Lemmatization is similar to stemming but it will return the proper lemma as opposed

to the word’s root, which may not be a meaningful word. For example, with stemming the

entities “car”, and “cars”, will be stemmed to “car,” but automobile will not. In lemmatization,

the words “car”, “cars,” and “automobile,” will all be reduced to the lemma “automobile”.

Several pre-packaged stemmers exist in most text mining tools (e.g., the Porter stemmer).

Similar to stop words, if the goal of the analysis is extracting the writing style, one may wish to

skip the stemming step as stemming often masks the tense used.

Text Analysis Extraction

Once the data has been pre-processed, the researcher can start analyzing the data. One

can distinguish between the extraction of individual words or phrases (entity extraction), the

extraction of themes or topics from the collective set of words or phrases in the text (topic

extraction), and the extraction of relationships between words or phrases (relation extraction).

Table 4 highlights these three types of analysis, the typical research questions investigated with

each approach, and some commonly used tools.

[Insert Table 4 here]

Entity (word) extraction. At the most basic level, text mining has been used in marketing

to extract individual entities (i.e., count words) such as person, location, brands, product

attributes, emotions, and adjectives. Entity extraction is probably the most commonly used text

analysis approach in marketing academia and practice partially due to its relative simplicity. It

allows the researcher to explore both what was written (the content of the words) as well as how

it was written (the writing style). Entity extraction can be used: (1) to monitor discussions on

social media (e.g., numerous commercial companies offer buzz monitoring services and use

entity extraction to track how frequently a brand is being mentioned across alternative social

media), (2) to generate a rich set of entities (words) to be used in a predictive model (e.g., what

are the words or entities associated with fake or fraudulent statements), and (3) as input to be

used with dictionaries to extract more complex forms of textual expressions such as a particular

concept, sentiment, emotion or writing style.

In addition to programming languages such as Python and R’s tm tool kits, software

packages such as Wordstat make it possible to extract entities without coding. Entity extraction

can also serve as input to be used in commonly used dictionaries or lexicons. Dictionaries (i.e., a

pre-defined list of words such as a list of brand names) are often used to classify entities into the

categories (e.g., concepts, brands, people, categories, locations). In more formal text,

capitalization can be used to help in extracting known entities such as brands. However, in less

formal text, such as social media, such signals are less useful. Common dictionaries include

LIWC (or Linguistic Inquiry and Word Count established by Pennebaker et al. 2015), EL 2.0

(Rocklage et al 2018), Diction 5.0, or General Inquirer for psychological states and traits (see

Berger and Milkman 2012; Ludwig et al. 2013; Netzer et al. 2019 for example applications).

Sentiment dictionaries such as Hedonometer (Dodds et al. 2011), VADER (Hutto and

Gilbert 2014) and LIWC can be used to extract the sentiment of the text. One of the major

limitations of the lexical approaches for sentiment analysis commonly-used in marketing is that

they apply a “bag of words” approach—meaning that word order doesn’t matter—and rely solely

on the co-occurrence of a word of interest (e.g., brand) with positive or negative words (e.g.,

“great” or “bad”) in the same textual unit (e.g., a review). While dictionary approaches may

provide easy approach to measure constructs and comparability across datasets, machine-

learning approaches trained by human-coded data (e.g., Hennig-Thurau et al. 2015; Borah and

Tellis 2016; Hartmann et al. 2018) tend to provide the most accurate way to measure such

constructs (Hartmann et al. 2019), particularly if the construct is complex or the domain is

uncommon. For this reason, researchers should carefully weigh the tradeoff between empirical fit

and theoretical commensurability, taking care to validate any dictionaries used in the analysis,

which we discuss in the next section.

A specific type of entity extraction includes linguistic-type entities such as part-of-speech

(POS) tagging, which assigns a linguistic tag (e.g., verb, noun, or adjective) to each entity. Most

text analysis tools (e.g., the tm package in R or the NLTK package in Python) have a built-in

POS tagging tool. If no pre-defined dictionary exists, or the dictionary is not sufficient for the

extraction needed, one could add hand-crafted rules to help define entities. However, the list of

rules can become long and the task of identifying and writing the rules can be tedious. If the

entity extraction by dictionaries or rules is difficult or if the entities are less well-defined,

machine learning supervised classification approaches, such as conditional random fields (Netzer

et al. 2012) and hidden Markov models, or deep learning (Timoshenko and Hauser 2019), can be

used to extract entities. The limitation of this approach is that often a relatively large hand-coded

training dataset needs to be generated.

To allow for a combination of words, entities can be defined as a set of consecutives

words often referred to as n-grams without attempting to extract the relationship between these

entities (e.g., the consecutive words “credit card” can create the uni-gram entities “credit” and

“card” as well as the bi-gram “credit card”). This can be useful if the researcher is interested in

using the text as input for a predictive model.

If the researcher wishes to extract entities while understanding the context in which the

entities were mentioned in the text (hence avoiding the limitation of the bag of words approach),

the emerging set of tools of word2vec or word embedding (Mikolov et al. 2013) can be

employed. Word2vec maps each word or entity to a vector latent dimensions called embedding

vector based on the words with which each focal word appears. This approach allows the

researcher to not only extract words but understand the similarity between words based on the

similarities between the embedding vectors (or the similarities between the sentences each words

appears in). Thus, unlike the previous approaches we discussed thus far, Word2vec preserves the

context in which the word appeared. While word embedding statistically captures the context in

which a word appears, it does not directly linguistically “understand” the relationships among

words.

Topic modeling. Entity extraction has two major limitations: (1) the dimensionality of the

problem (often thousands of unique entities are extracted) and (2) the interpretation of many

entities. Several topic modeling approaches have been suggested to overcome these limitations.

Similar to how factor analysis identifies underlying themes among different survey items, topic

modeling can identify the general topics (described as a combination of words) that are discussed

in a body of text. This text summarization approach increases understanding of document content

and is particularly useful when the objective is insight generation and interpretation rather than

prediction (e.g., Berger and Packard 2018; Tirunillai and Tellis 2014). Additionally, monitoring

topics, as opposed to words, makes it easier to assess how discussion changes over time (e.g.,

Zhong and Schweidel 2019).

Methodologically, topic modeling mimics the data generating process in which the writer

chooses the topic she wants to write about and then chooses the words to express these topics.

Topics are defined as word distributions that commonly co-occur and hence have a certain

probability of appearing in a topic. A document is then described as a probabilistic mixture of

topics.

The two most commonly used tools for topic modeling are Latent Dirichlet Allocation

(LDA; Blei et al. 2003) and Poisson Factorization (PF; Gopalan et al. 2013). The predominant

approach prior to LDA and PF was the Support-Vector-Machine Latent Semantic Analysis

(LSA) approach. While LSA is simpler and faster to implement relative to LDA and PF, it

requires larger textual corpora and it often achieves lower accuracy levels. Other approaches

include building an ontology of topics using a combination of human classification of documents

as seeding for a machine learning classification (e.g., Moon and Kamakura 2017). Whereas LDA

is often simpler to apply than PF, PF has the advantage of not assuming that the topic

probabilities have to sum up to one. That is, some documents may have more topic presences

than others, and a document can have multiple topics with high likelihood of occurrence.

Additionally, PF tends to be more stable with shorter text. Buschken and Allenby (2016) relax

the common “bag of words” assumption underlying the traditional LDA model, leveraging the

within sentence dependencies of online reviews. Another approach to assess topics, while

accounting for the sequence context in which the word appears, is LDA2vec (Moody 2016). In

the context of search queries, Liu and Toubia (2018) further extend the LDA approach to

hierarchical LDA for cases in which related documents (queries and search results) are used to

extract the topics. Additionally, the researcher can use an unsupervised or seeded LDA approach

to incorporate prior knowledge in the construction and interpretation of the topics (e.g., Puranam

et al. 2017; Toubia et al. 2018).

While topic modeling methods often produce very sensible topics, because topics are

selected solely based on a statistical approach, the selection of the number of topics and the

interpretation of some topics can be challenging. It is recommended to combine both statistical

approaches (e.g., the perplexity measure, which is a model-fit based measure) and researcher

judgment in selecting the number of topics.

Relation extraction. At the most basic level relationships between entities can be

captured by the mere co-occurrence of entities (e.g., Netzer et al. 2012; Toubia and Netzer 2017;

Boghrati and Berger 2019). However, marketing researchers are often more interested in

identifying textual relationships among extracted entities such as the relationships between

products, attributes, and sentiments. Such relationship are often more relevant for the firm than

merely measuring the volume of brand mentions or even the overall brand sentiment. For

example, researchers may want to identify whether consumers mentioned a particular problem

with a specific product feature. Feldman et al. (2015) and Netzer et al. (2012) provide such

examples by identifying the textual relationships between drugs and adverse drug reactions that

imply that a certain drug may cause a particular adverse reaction.

Relation extraction also offers a more advanced route to capture sentiment by providing

the link between an entity of interest (e.g., a brand) and the sentiment expressed beyond their

mere co-occurrence. Relation extraction based on bag-of-words approach, which treats the

sentence as a bag of unsorted words looking at the co-occurrence is limited because it the co-

occurrence of words may not imply relationship between words. For example, the co-occurrence

of a drug (e.g., Advil) with a symptom (e.g., Headache) may refer to the symptom as a side effect

of the drug or as the effect the drug is aiming to help with. Addressing such relationships

requires identifying the sequence of words and the linguistic relationship among them. There

have only been limited applications of such relation extraction in marketing, primarily due to the

computational and linguistic complexities involved in accurately making such relational

inferences from unstructured data (see e.g., the diabetes drugs application in Netzer et al. 2012).

However, as the methodologies used to extract entity relations evolve, we expect this to be a

promising direction for marketers to take.

The most commonly used approaches for relation extraction are hand-written relationship

rules, supervised machine learning approaches, and a combination of these approaches. At the

most basic level, the researcher could write a set of rules that describe the required relationship.

An example of such a rule may be the co-occurrence of product (e.g., “Ford”), attribute (e.g., “oil

consumption”) and problem (e.g., “excessive”). However, such approaches tend to require many

hand-written rules and have low recall (they miss many relations), and hence are becoming less

popular.

A more common approach is to train a supervised machine learning tool. This could be

linguistic agnostic approaches (e.g., deep learning) or NLP (Natural Language Processing)

approaches that aim to understand the linguistic relationship in the sentence. Such an approach

requires a relatively large training dataset provided by human coders in which various

relationship (e.g., sentiment) are observed. One readily available tool for NLP-based relationship

extraction is the Stanford Sentence and Grammatical Dependency Parser

(http://nlp.stanford.edu:8080/parser/). The tool identifies the grammatical role of different words

in the sentence to identify their relationship. For example, to assign a sentiment to a particular

attribute, the parser first identifies the presence of an emotion word and then, in cases where a

subject is present, automatically assesses if there is a grammatical relationship (e.g., the

sentence: “the hotel was very nice”, the adj. “nice” relates to the subject “hotel”). As with many

off-the-shelf tools the validity of the tool for a specific relation extraction needs to be tested.

Finally, beyond the relations between words/entities within one document, text can also

be investigated across documents (e.g., online reviews or academic articles). For example, a

temporal sequence of documents or a portfolio of documents across a group or community of

communicators can be examined for interdependencies (Ludwig et al. 2013, Ludwig et al. 2014).

Text Analysis Metrics

Early work in marketing has tended to summarize unstructured text with structured

proxies for these data. For example, in online reviews, researchers have used volume (e.g., Godes

and Mayzlin 2004; Moe and Trusov 2011), valence, often captured by numeric ratings that

supplement the text (e.g., Ying et al. 2006; Godes and Silva 2012; Moe and Schweidel 2012),

and variance, often captured using entropy-type measures (e.g., Godes and Mayzlin 2004).

However, these quantifiable metrics often mask the richness of the text. Several common metrics

are often used to quantify the text itself, as explained next.

Count measures. Count measures have been used to measure the frequency of each entity

occurrence, entities co-occurrence, or entities relations. For example, when using dictionaries to

evaluate sentiment or other categories, researchers often use the proportion of negative and/or

positive words in the document, or the difference between the two (Berger and Milkman 2012;

Borah and Tellis 2016; Pennebaker et al. 2015; Schweidel and Moe 2014; Tirunillai and Tellis

2014). The problem with simple counts is that longer documents are likely to include more

occurrences of every entity. For that reason, researchers often look at the proportions of words in

the document that belong to a particular category (e.g., positive sentiment). The limitation of the

simple measure of proportion of words in the document is that some words are more likely to

appear than others. For example, the word “laptop” is likely to appear in almost every review in

corpora that is built of laptop reviews.

Accuracy measures. When evaluating the accuracy of text measures relative to human-

coded or externally validated documents, measures of recall and precision are often used. Recall

is the proportion of entities in the original text that the text-mining algorithm was able to

successfully identify (it is defined by the ratio of true positive to the sum of true positives and

false negatives). Precision is the proportion of correctly identified entities from all entities

identified (it is defined by the ratio of true positives to the sum of true positives and false

positives). Taken on their own, recall and precision measures are difficult to assess because an

improvement in one often comes at the expense of the other. For example, if one defines that

every entity in the corpora is a brand, recall for brands will be perfect (you will never miss a

brand if it exists in the text), but precision will be very low (there will be many false positive

identifications of a brand entity).

To create the balance between recall and precision one can use the F1 measure—a

harmonic mean of the levels of recall and precision. If the researcher is more concerned with

false positives versus false negatives (e.g., it is more important to identify positives than

negatives) different weighting can be given to recall and precision. Alternatively, for unbalanced

data with high proportions of true or false in the populations a Receiver Operating

Characteristics (ROC) curve can be used to reflect the relationship between true positives and

false positives and the area under the curve is often used as a measure of accuracy.

Similarity measures. In some cases, the researcher is interested in measuring the

similarity between documents (e.g., Ludwig et al. 2013). How similar is the language used in two

advertisements? How different is a song from its genre? In such cases measures such as linguist

style matching, similarity in topic use (Berger and Packard 2018), cosine similarity and the

Jaccard Index (e.g., Toubia and Netzer 2017) can be used to assess the similarity between the

text in one document relative to the text in another document.

Readability measures. In some cases, the researcher is interested in evaluating the

readability of the text. Readability can reflect the sophistication of the writer and/or the ability of

the reader to comprehend the text (e.g., Ghose and Ipeirotis 2011). Common readability

measures include the Flesch-Kindcaid Reading Ease and the Simple Measure of Gobbledygook

(SMOG) measures. These measures often use metrics such as average number of syllables and

average number of words per sentence to evaluate the readability of the text. Readability

measures often grade the text on a 1-12 scale reflecting the U.S. school grade-level needed to

comprehend the text. Common text-mining packages have readability tools built in.

THE VALIDITY OF TEXT-BASED CONSTRUCTS

While the availability of text has opened up a range of research questions, for textual data

to provide value, one must be able to establish its validity. Both internal validity (i.e., does text

accurately measure the constructs and the relationship between them?) and external validity (i.e.,

do the test-based findings apply to phenomena outside the study?) can be established in various

ways (Humphreys and Wang 2017). Table 5 describes how the text analysis can be evaluated to

improve different types of validity (Cook and Campbell 1979).

[Insert Table 5 here]

Internal Validity

Internal validity is often of major threat in the context of text analysis because the

mapping between word and the underlying dimension the research wants to measure (e.g.,

psychological state and traits) is rarely straight forward and can vary across contexts and textual

outlets (e.g., formal news versus social media). Additionally, given the relatively young field of

automated text analysis, validation of many of the methods and constructs is still on-going.

Accordingly, it is important to confirm the internal validity of the approach used. A range

of methods can be adopted to ensure construct, concurrent, convergent, discriminant, and causal

validity. In general, the approach for ensuring internal validity is to be sure that the text studied

accurately reflects the theoretical concept or topic being studied, does so in a way that is

congruent with prior literature, is discriminant from other, related constructs, and provides ample

and careful evidence for the claims of the research.

Construct validity—does the text represent the theoretical concept?—is perhaps the most

important to address when studying text. Threats to construct validity occur when the text

provides improper or misleading evidence of the construct. For instance, researchers often rely

on existing, standardized dictionaries to extract constructs to ensure that their work is

comparable with other work. However, these dictionaries may not always fit the particular

context. For example, extracting sentiment from financial reports using sentiment tools

developed for day-to-day language may not be appropriate. Particularly when attempting to

extract complex constructs (such as psychological states and traits, relationships between

consumers and products, and even sentiment), researchers should attempt to validate the

constructs on the specific application to ensure that what is being extracted from the text is

indeed what they intended to extract. Construct validity can also be challenged when homonyms

or other words do not accurately reflect what researchers think they do

Strategies for addressing threats to construct validity require that researchers examine

how the instances counted in the data connect to the theoretical concept or concepts (Humphreys

and Wang 2017). Dictionaries can also be validated using a saturation approach, pulling a

subsample of coded entries and verifying with a hit rate of approximately 80% (Weber 2005).

Another method is to use input from human coders, as is done to support machine learning

applications as previously discussed. For example, one can use Amazon Mechanical Turk

workers to label phrases on a scale from very negative to very positive for sentiment analysis and

then use these words to create a weighted dictionary. In many cases, multiple methods for

dictionary validation are advisable to ensure that one is achieving both theoretical and empirical

fit. For topic modeling, researchers infer topics from a list of co-occurring words. However,

these are theoretical inferences made by researchers. As such, construct validity is equally

important, and can be ascertained through some of the same methods of validation through

saturation and calculating a hit rate through manual analysis of a subset of the data. When using

a classification approach, confusion matrices can be produced to provide details on accuracy,

false positives, and false negatives (Das and Chen 2007).

Concurrent validity concerns the way that the researcher’s operationalization of the

construct relates to prior operationalizations. Threats to concurrent validity often come when

researchers create text-based measures inductively from the text. For instance, if one develops a

topic model from the text, it will be based on the dataset and may not therefore produce topics

that are comparable with previous research. To address these threats, one should compare the

operationalization with other research and other data sources. For example, Schweidel and Moe

(2014) propose a measure of brand sentiment based on social media text data and validate it by

comparing it to brand measures obtained through a traditional marketing research survey.

Similarly, Netzer et al. (2012) compare the market structure maps derived from textual

information to those derived from product switching and surveys, and Tirunillai and Tellis

(2014) compare the topics they identify to those found in Consumer Reports. When studying

linguistic style (Pennebaker and King 1999), for example, robust measures from prior literature

where factor analysis and other methods have been employed to create the construct.

Convergent validity ensures that multiple measurements of the construct (i.e. words) all

converge to the same concept. Convergent validity can be threatened when the measures of the

construct do not align or have different effects. Convergent validity can be enhanced by using

several substantively different measures (e.g. dictionaries) of the same construct to look for

converging patterns For example, when studying posts about the stock market, Das and Chen

(2007) compare five different classifiers for measuring sentiment, comparing them in a

confusion matrix to examine false positives. Convergent evidence can also come from creating a

correlation or similarity matrix of words or concepts and checking for patterns that have face

validity. For instance, Humphreys (2010) looks for patterns between the concept of crime and

negative sentiment to provide convergent evidence that crime is negatively valenced in the data.

Discriminant validity, the degree to which the construct measures are sufficiently

different from measures of other constructs, can be threatened when the measurement of the

construct is very similar to another construct. For instance, measurements of sentiment and

emotion in many cases may not seem different because they are measured using similar word

lists or, when using classification, return the same group of words as predictors. Strategies for

ensuring discriminant validity entail looking for discriminant rather than convergent patterns and

boundary conditions (i.e. when and how is sentiment different from emotion?). Further,

theoretical refinements can be helpful in drawing finer distinctions. For example, anxiety, anger,

and sadness are different kinds of emotion (and can be measured via psychometrically different

scales) while sentiment is usually measured as positive, negative or neutral (Pennebaker et al.

2015).

Causal validity, is the degree to which the construct, as operationalized in the dataset,

actually the cause of another construct or outcome, is best ascertained through random

assignment in controlled lab conditions. Any number of external factors can threaten causal

validity. However, steps can be taken to enhance causal validity in naturally-occurring textual

data. In particular, rival hypotheses and other explanatory factors for the proposed causal

relationship can be statistically controlled for in the model. For example, Ludwig et al (2013)

include price discount in the model when studying the relationship between product reviews and

conversion rate to control for this factor.

External Validity

To achieve external validity, researchers should make attempts to ensure that the effects

found in text apply outside of the research framework. Because text analysis often uses naturally-

occurring data, and often of large magnitude, it tends have relatively high degree of external

validity relative to, for example, lab experiments. However, establishing external validity is still

necessary due to threats to validity from sampling bias, overfitting, and single-method bias. For

example, online reviews, may be biased due to self-selection among those who elected to review

a product (Schoenmueller et al. 2019).

Predictive validity is threatened when the construct, although perhaps properly measured,

does not have the expected effects on a meaningful second variable. For example, if consumer

sentiment falls, but customer satisfaction remains high, predictive validity could be called into

question. To ensure predictive validity, text-based constructs can be linked to key performance

measures such as sales (e.g., Fossen and Schweidel 2019) or consumer engagement (Ashley and

Tuten 2015). If a particular construct has been theoretically linked to a performance metric, then

any text-based measure of that construct should also be linked to that performance metric.

Tirunillai and Tellis (2012) show that volume of Twitter activity affects stock price, but find

mixed results for the predictive validity of sentiment, with negative sentiment being predictive,

but positive sentiment having no effect.

Generalizability can be threatened when basing results on a single dataset because we do

not know if the findings, model, or algorithm would apply in the same way to other texts or

outside of textual measurements. Generalizability of the results can be established by viewing the

results of text analysis along with other measures of attitude and behavioral outcomes. For

example, Netzer et al. (2012) test their substantive conclusions and methodology on both

message boards of automobile discussion and drug discussion from WebMD. Evaluating the

external validity and generalizability of the findings is key, because the analysis of text drawn

from a particular source may not reflect consumers more broadly (e.g., Schweidel and Moe

2014).

Robustness can be limited when there is only one metric or method used in the model.

Robustness can be ensured by using different measures for relationships (e.g. Pearson

correlation, cosine similarity, lift) and probing results by relaxing different assumptions. The use

of holdout samples and k-fold cross validation methods can aid researchers from overfitting their

models and ensure that relationships found in the dataset would hold with other data as well

(Jurafsky et al. 2014; see Humphreys and Wang 2017). Probing on different “cuts” of the data

can also help. Berger and Packard (2018), for example, compare lyrics from different genres, and

Ludwig et al. (2013) include reviews of both fiction and non-fiction books.

Finally, researchers should bear in mind the limitations of text itself. There are thoughts

and feelings that consumers, managers, or other stakeholders may not express in text. The form

of communication (e.g., Tweets, annual reports) may also shape the message. Some constructs

may not be explicit enough to be measured with automated text analysis. And while textual

information can often involve large samples, these samples may not be representative. Twitter

users, for example, tend to be younger and more educated (Pew Research 2018). Those who

contribute textual information, particularly in social media, may represent polarized points of

view. When evaluating cultural products or social media, one should consider the system in

which they are generated. Often viewpoints are themselves filtered through a cultural system

(Hirsch 1986; McCracken 1988) or elevated via an algorithm, and what products make it through

this process may share certain characteristics. For this reason, researchers and firms should use

caution when making attributions based on cultural text. It is not necessarily a reflection of

reality (Jameson 2005) but may rather represent ideals, extremes, or institutionalized perceptions

depending on the context.

FUTURE RESEARCH AGENDA

We hope this paper encourages more researchers and practitioners to think about how

they can incorporate textual data into their research. Communication and linguistics are at the

core of studying text in marketing. Automated text analysis opens the black-box of interactions,

allowing researchers to directly access what is being said and how it is said in marketplace

communication. Using text as indicative of meaning-making processes opens fascinating and

truly novel research questions and challenges. There are many methods and approaches

available, and there is no space to do all of them justice. While we have discussed several

research streams, given its novelty there are still ample opportunities for future research to which

we turn now.

Using Text to Reach Across the Marketing Discipline

Returning to how text analysis can unite the tribes of marketing, it is worth highlighting a

few areas mostly examined by one research tradition in marketing where fruitful cross-

pollination between tribes is possible through text analysis.

Brand communities were first identified and studied by researchers coming from a

sociology perspective (Muniz and O’Guinn 2001). Later, qualitative and quantitative researchers

have further refined the concepts, identifying a distinct set of roles and status in the community

(e.g. Mathwick et al. 2007). But automated text analysis allows researchers to study how

consumers in these communities interact at scale and in a more quantifiable manner. For

example, examining how people with different degrees of power use language and predict group

outcomes based on quantifiably different dynamics (e.g., Manchanda et al. 2015). Researchers

can track influence, for example, looking at which types of users initiate certain words of phrases

and which others pick up on them. One can examine whether people begin to enculturate to the

language of the community over time and predict which individuals may be more likely to stay

or leave, based on how well they adapt to the groups’ language (Danescu-Niculescu-Mizil et al.

2013; Srivastava and Goldberg 2017). Quantitative or machine learning researchers might

capture the most common of topics that members talk about and how these dynamically change

over the evolution of the community. Interpretive researchers might look for how these terms

link conceptually, to find underlying community norms that lead members to stay on. Marketing

strategy researchers might then use or develop dictionaries to connect these communities to firm

performance and to offer directions for firms regarding how to keep members participating

across different brand communities (or contexts).

The progression can flow the other way as well. Outside of a few early investigations

(e.g., Dichter 1966), word of mouth was originally studied by quantitative researchers, interested

in whether interpersonal communication actually drove individual and market behavior (e.g.,

Chevalier and Mayzlin 2006; Iyengar et al. 2010; Godes and Mayzlin 2009). More recently,

however, behavioral researchers have begun to study the underlying drivers of word of mouth,

looking at why people talk about and share some stories, news, and information rather than

others (Berger and Milkman 2012; DeAngelis et al. 2012; see Berger 2014 for a review).

Marketing strategy researchers might track the text of word of mouth interaction to predict the

emergence of brand crises or social media firestorms (e.g., Zhong and Schweidel 2019) and

when, if, and how to respond (Herhausen et al. 2019).

Consumer-firm interaction can also be a rich area to examine. Behavioral researchers

could use the data from call centers to better understand interpersonal communication between

consumers and firms and what drives customer satisfaction (e.g., Packard et al. 2018; Packard

and Berger 2019). The back and forth between customers and agents could be used to understand

conversational dynamics. More quantitative researchers can use the textual features of call

centers to predict outcomes such as churn, and even go beyond text to examine vocal features

such as tone, volume, and speed of speech. Marketing strategy researchers could use calls to

understand how customer centric a company is or assess the quality, style, and impact of its sales

personnel.

Finally, it is worth noting that different tribes not only have different skill sets, but also

often study substantively different types of textual communication. Consumer-to-consumer

communication is often studied by researchers in consumer behavior while marketing strategy

researchers may tend to more often study firm-to-consumer and firm-to-firm communication.

Collaboration among researchers from the different sub-fields may also allow to combine these

different sources of textual data. There is ample opportunity to apply theory developed in one

domain to enhance another. Marketing strategy researchers, for example, often use transaction

economics to study business to business relationships through agency theory. But these

approaches may be equally beneficial to studying consumer-to-consumer communications.

Broadening the Scope of Text Research

As noted in Table 1, certain text flows have been studied more than others. A large

portion of existing work has focused on consumers communicating to one another through social

media and online reviews. The relative availability of such data has made it a rich area to study,

and an opportunity to explore applying text-analysis to marketing problems.

Further, for this

area to grow, researchers need to branch out. This includes expanding (a) data sources, (b) actors

examined, and (c) research topics. `

Expand data sources used. Offline word of mouth, for example, can be examined to

study what people talk about and conversational dynamics. Doctor-patient interactions can be

studied to understand what drives medical adherence. And text items such as yearbook entries,

notes passed between students, or the text of speed dating conversations can be used to examine

relationship formation, maintenance, and dissolution. Using offline data requires carefully

transcribing content, which increases the amount of effort required, but opens up a range of

interesting avenues of study. For example, we know very little on the differences between online

recommendations and face-to-face recommendations, where the latter also include the interplay

between verbal and non-verbal information. Moreover, in the new era of “perpetual contact” our

understanding of cross-message and cross-channel implications is limited. Research by Batra and

Keller (2016) and Villaroel et al. (2018) suggests that appropriate sequencing of messages

While readily available data facilitates research, there are downsides to be recognized including the representatives

of such data and the terms of service that govern the use of these data.

matters; it might similarly matter across channels and modality. Given the rise of technology-

enabled realities (e.g., Augmented Reality, Virtual Reality, Mixed Reality), assistive robotics,

and smart speakers, understanding the role and potential difference communication and verbal

cues play could be achieved using these novel data sources.

Expand dyads between text producers and text receivers. There are numerous dyads

relevant to marketing where text plays a crucial role. We discuss just a few of the areas that

deserve additional research.

Considering consumer-firm interactions, we expect to see more research leveraging the

rich information exchanged between consumers and firms through call center and chats (e.g.,

Packard et al. 2018; Packard and Berger 2019). These interactions often reflect inbound

communication between customers and firm, which can have important implications for the

relationship between parties. In addition, how might the language used on packaging or in brand

mission statements reflect the nature of organizations and their relationship to their consumers?

How might the language that is most impactful in sales interactions differ from the language that

is most useful in customer service interactions? Research may also probe how the impact of such

language varies across contexts. The characteristics of language used by CPG brands and

pharmaceuticals brands in direct to consumer advertising may likely differ. Similarly, the way in

which consumers process the language used in disclosures in advertisements for pharmaceuticals

(e.g., Narayanan et al. 2004) and political candidates (e.g., Wang et al. 2018) may vary.

Turning to firm-to-firm interactions, most conceptual frameworks on B2B exchange

relations emphasize the critical role of communication (e.g., Palmatier et al. 2007).

Communicational aspects have been linked to important B2B relational measures such as

commitment, trust, dependence, relationship satisfaction and relationship quality. Yet research

on actual, word-level B2B communication is very limited. For example, very little research has

examined the types of information exchanged between salespeople and customers in offline

settings. The ability to gather and transcribe data at scale points to important opportunities to do

so. As for within-firm communication, what about the informal communications such as emails,

memos and agendas about marketing that firms generate, and that their employees consume?

Similarly, while a great deal of work in accounting and finance has begun to use annual

reports as a data source (see Loughran and McDonald 2016 for a review), there has been less

attention to this area in marketing to study communication with investors. Most research has used

this data to predict outcomes such as stock performance and other measures of firm valuation.

Given recent interest in linking marketing related activities to firm valuation (e.g., McCarthy and

Fader 2018), this may be an area to pursue further. All firm communication, including required

documents such as annual reports or discretionary forms of communication such as advertising

and sales interactions can be used to measure variables such as market orientation, marketing

capabilities, marketing leadership styles, and even a firm’s brand personality.

There is also ample research opportunity into interactions between consumers, firms, and

society. Data about the broader cultural and normative environment of firms such as news media

and government reports may be useful to understand the forces that shape markets. To

understand how a company such as Uber navigates resistance to market change, for example, one

might study transcripts of town hall meetings and other government documents where citizen

input is heard and answered. Exogenous shocks in the forms of social movements such as

#metoo and #blacklivesmatter have affected marketing communication and brand image. One

potential avenue for future research is to take a cultural branding approach (Holt 2016) to study

how different publics define, shape, and advocate for certain meanings in the marketplace. Firms

and their brands do not exist in a vacuum, independent of the society in which they operate. Yet,

limited research in marketing has considered how text can be used to derive firms’ intentions and

actions at the societal level. For example, scholars have shown how groups of consumers such as

locavores (i.e., people who eat locally grown food, Thompson and Coskuner-Balli 2007),

fashionistas (Scaraboto and Fischer 2012), and bloggers (McQuarrie et al. 2012) shape markets.

Through text analysis, the effect of the intentions of these social groups of the market can then be

measured and better understood.

Another opportunity is using textual data to study culture and cultural success. Topics

such as cultural propagation, artistic change, and the diffusion of innovations have been

examined across disciplines with the goal of understanding why certain products succeed while

others fail (Bass 1969; Boyd and Richerson 1985; Cavalli-Sforza and Feldman 1981; Rogers

1995; Salganik et al. 2006; Simonton 1980). While success may be random (Bielby and Bielby

1994; Hirsh 1972), another possibility is that cultural items succeed or fail based on their fit with

consumers. By quantifying aspects of books, movies, or other cultural items quickly and at scale,

researchers can measure whether concrete narratives are more engaging, or more emotionally

volatile movies are more successful. Whether songs that use certain linguistic features are more

likely to top the billboard charts and whether books that evoke particular emotions sell more

copies. While not as widely available as social media data, more and more data on cultural items

has recently become available. Datasets such as the Google Books Corpus, song lyrics websites,

or movie script database provide a wealth of information. Such data could enable analyses of

narrative structure to identify of “basic plots” (e.g. Reagan et al. 2016, van Laer et al. 2019).

Key Marketing Constructs (that Could Be) Measured with Text

Beginning with previously developed ways of representing marketing constructs can help

some researchers address validity concerns. This section details a few of these constructs to aid

researchers who are beginning to use text analysis in their work (see Web Appendix). Using

prior operationalization of a construct can ensure concurrent validity—helping to build the

literature in a particular domain—but researchers should take steps to ensure that the prior

operationalization has construct validity with their dataset.

At the individual level, sentiment and satisfaction are perhaps some of the most common

measurements (e.g. Schweidel and Moe 2014; Büschken and Allenby, 2016; Homburg et al.

2015; Herhausen et al. 2019; Ma et al. 2015) and have been validated in numerous contexts.

Other aspects that may be extracted from text include the authenticity and emotionality of

language, which have also been explored based on robust surveys, scales, or combining multiple

existing measurements (e.g. Mogilner et al. 2011; van Laer et al. 2019). There are also

psychological constructs such as personality type and construal level (Kern et al. 2016; Snefjella

and Kuperman 2015) that are potentially useful for marketing researchers, which could also be

inferred from the language used by consumers.

Future work in marketing studying individuals might consider measurements of social

identification and engagement. That is, researchers currently have an idea of positive or negative

consumer sentiment, but are only beginning to explore emphasis (e.g. Rocklage and Fazio 2015),

trust, commitment, and other modal properties. To this end, harnessing linguistic theory of

pragmatics and examining phatics over semantics could be useful (see e.g. Villaroel et al. 2017).

Once developed, we recommend to carefully validate approaches proposed to measure such

constructs along the lines described previously.

At the firm level, constructs have been identified in firm-produced text such as annual

reports and press releases. Market orientation, advertising goals, future orientation, deceitful

intentions, firm focus, and innovation orientation have all been measured and well validated

using this material (Table 6). Work in organizational studies has a longer history of using text

analysis in this area, and might provide some inspiration and validation by studying the existence

of managerial frames for sensemaking and the effect of activists on firm activities.

Future work in marketing on the firm level could further refine and diversify

measurements of strategic orientation (e.g. innovation orientation, market-driving vs. market-

driven orientations). Difficult-to-measure factors deep in the organizational culture, structure, or

capabilities may be revealed in the words the firm, its employees, and external stakeholders use

to describe it (see Molner et al. 2019). Likewise, the mind-sets and management style of

marketing leaders may be discerned from the text they use (see Yadav et al. 2007). Firm

attributes such as brand value that are important outcomes of firm action could also be explored

using text (e.g., Herhausen et al. 2019). In this case, there is an opportunity to use new kinds of

data. For instance, internal, employee-based brand value could be measured via text on LinkedIn

or Glassdoor. Lastly, more subtle attributes of firm language including conflict, ambiguity, or

openness might provide some insight into the effects of managerial language on firm success.

For this, looking at less formal textual data of interactions such as employee emails, salesperson

calls, or customer service center calls may be useful.

Less work in marketing has measured constructs on the social or cultural level, but work

in this vein tends to look at how firms fit into the cultural fabric of existing meanings and norms.

For instance, institutional logics and legitimacy have been measured by analyzing media text, as

has the rise of brand publics that increase discussion of brands within a culture (Arvidsson and

Caliandro 2016).

At the level of culture, marketing research is likely to maintain a focus on how firms fit

into the cultural environment, but may also look to how the cultural environment affects

consumers. For instance, measurement of cultural uncertainty, risk, hostility, and change could

benefit researchers interested in the effects of culture on both consumer and firm effects as well

as the effects of culture and society on government and investor relationships. Measuring

openness and diversity through text are also timely topics to explore and might inspire

innovations in measurement, looking for example, at language diversity rather than focusing on

the specific content of language. Important cultural discourses such as language around debt and

credit could also be better understood using text analysis. Measurement of gender and race-

related language can be useful to explore diversity and inclusion in the way firms and consumer

react to text originated from a diverse set of writers.

Opportunities and Challenges Provided by Methodological Advances

Opportunities. As the development of text analysis tools advances, we expect to see new

and improved use of these tools in marketing, which can enable answering questions we could

not previously address or address only in a limited manner. Here are a few specific method-

driven directions that seem promising.

First, the vast majority of the approaches used for text analysis in marketing (and

elsewhere) rely on “bag of words” approaches hence capturing true linguistic relationship among

words beyond co-occurrence of words was limited. However, in marketing we are often

interested in capturing the relationship among entities. For example, what problems or benefits

did the customer mention about a particular feature of a particular products? Such approaches

require capturing deeper textual relationship among entities than is commonly used in marketing.

We expect to see future development in these areas as deep learning and NLP linguistic-based

approaches allows us to better capture semantic relationships.

Second, in marketing we are often interested in the latent intention or latent states of

writers when writing the text such emotions, personality and motivations. Most of the research in

this area has primarily relied on a limited sets of dictionaries (primarily the LIWC dictionary)

developed and validated to capture such constructs. However, these dictionaries are often limited

in capturing nuanced latent states or latent states that may have different manifestation across

different contexts. Similar to advances made in areas such image recognition with the availability

of a large number of human-coded training data (often in the millions) combined with deep

learning tools, we hope to see similar approaches being taken in capturing more complex

behavioral states from text in marketing. This would require an effort to human code a large and

diverse set of textual corpora for a wide range of behavioral states. Transfer learning methods

commonly used in deep learning tools such as conventional neural nets can then be used to apply

the learning from the more general training data to any specific application.

Third, there is also the possibility of using text analysis to personalize customer-firm

interactions. Using machine learning, text analysis can also help personalize the customer

interaction by detecting consumer traits such as personality, states such as urgency or irritation,

and perhaps eventually predicting traits associated with value to the firm such as customer

lifetime value. After analysis, firms can then tailor customer communication to match linguistic

style and perhaps funnel consumers to the appropriate firm representative. The stakes of making

such prediction may be high, mistakes costly, and there are clearly contexts in which using

artificial intelligence impedes constructing meaningful customer-firm relationships (e.g.

healthcare; Longoni et al. 2019).

Fourth, while our discussion has focused on textual content, text is just one example of

unstructured data such as audio, video and image. Social media posts often marry text with

images or videos. Print advertising usually overlays text on a carefully constructed visual.

Television advertising, while it may not include text on the screen that consumers read, has an

audio track that contains text and a video that progress simultaneously.

Up until recently, text data has received the most attention, mainly due to the presence of

tools to extract meaningful features. That said, tools such as Praat (Boersma, 2001) allow

researchers to extract information from audio (e.g., Van Zant and Berger 2019). One of the

advantages of audio data over text data is that it provides richness in the form of tone and voice

markers that can add to the actual words expressed (e.g., Xiao et al. 2013). This allows

researchers to look at just not was said, but how it was said, examining how pitch, tone, and

other vocal or paralinguistic features shape behavior.

Similarly, recent research has developed approaches to analyze images (e.g., Liu et al.

2018), either characterizing the content of the image or identifying features within an image.

Research into the impact of the combination of text and images is sparse (e.g., Hartmann et al.

2019). For example, images can be described in terms of colors that appear in the images. In the

context of print advertising, textual content may be less persuasive when used in conjunction

with images of a particular color palette, while other color palettes may enhance the

persuasiveness of text. Used in conjunction with simple images, the importance of text may be

quite pronounced. But, when paired with complex imagery, viewers may attend primarily to the

image, diminishing the impact of text. If this is the case, legal disclosures that are literally part of

an advertisement’s fine print may not attract the audience’s attention.

Analogous questions arise as to the role that text plays when incorporated into videos.

Research has proposed approaches to characterize video content (e.g., Liu et al. 2018). In

addition to comprising the script of the video, text may also appear visually. In addition to the

audio context in which text appears, its impact may depend on the visuals that appear

simultaneously. It may also be the case that its position within a video relative to the start may

moderate its effectiveness. For example, emotional text content that is spoken later in a video

may be less persuasive for a number of reasons. The audience may have ceased paying attention

by the time the text is spoken. Alternatively, the visuals with which the audio is paired may be

more compelling to viewers or the previous content of the video may have depleted a viewer’s

attentional resources. As our discussion of both images and videos suggests, text is but one

component of marketing communications. Future research must investigate its interplay with

other characteristics, including not only the content in which it appears, but also when it appears

(e.g., Kanuri et al. 2018) and in what media.

Challenges. While there are a range of opportunities, textual data also brings with it

various challenges. First, is the interpretation challenge. In some ways, text analysis seems to

provide more objective ways of measuring behavioral processes. Rather than asking people how

much they focused on themselves versus others when sharing word of mouth, for example, one

can count the number of first person (e.g., “I”) and second person pronouns (e.g., “you”, Barasch

and Berger 2014), providing what seems more like ground truth. But while part of this process is

certainly more objective (e.g., the number of different types of pronouns), the link between such

measures and underlying processes (i.e., what it says about the word of mouth transmitter) still

requires some degree of interpretation. Other latent modes of behavior are even more difficult to

count. While some words (e.g., “love”) are generally positive, for example, how positive they are

may depend heavily on idiosyncratic individual difference as well as the context.

More generally, there is challenge and opportunity in understanding the context in which

textual information appears. While early work in the space, particularly using entity extraction,

asked questions such as how much emotion is in a passage of text, more accurate answers to that

question take must take context into account. A restaurant review may contain lots of negative

words, for example, but does that mean the person hates the food, the service, or the restaurant

more generally? Songs that contain more second person pronouns (e.g., “you”) may be more

successful (Packard and Berger 2019), but to understand why, it helps to know whether the lyrics

use you as the subject or object of the sentence. Context provides meaning, and the more one

understands not just which words are being used, but how they are being used, the easier it will

be to extract insight. Dictionary-based tools are particularly susceptible to variation in the

context in which the text appear, as dictionaries are often created in a context free environment

to match multiple contexts. Whenever possible, it is advised to use a dictionary that was created

for the specific context (e.g., the financial sentiment tool develop by Loughran and McDonald

(2011)).

As mentioned earlier, there are also numerous methodological challenges. Particularly

when exploring the “why,” hundreds of features can be extracted, making it important to think

about multiple hypothesis testing (and use of Bonferroni and other corrections). Only the text

used by the text creator is available, so in some sense there is self-selection. Both the individuals

who decide to contribute and the topics people decide to bring up in their writing may suffer

from self-selection. Particularly when text is used to measure (complex) behavioral constructs

validity of the constructs need to be considered. Also, for most researchers, analyzing textual

information requires retooling and learning a whole new set of skills.

Data privacy challenges represent a significant concern. Research often uses online

product reviews and sales ranking data scraped from website (e.g., Wang et al. 2013) or

consumers’ social media activity scraped from the platform (e.g., Godes and Mayzlin 2004;

Tirunillai and Tellis 2012). Though such approaches are common, legal questions have started to

arise. LinkedIn was unsuccessful in its attempt to block a startup company from scraping data

that was posted on users’ public profiles (Rodriguez 2017). While scraping public data may be

permissible under the law, it may come into conflict with terms of service of those platforms that

have data of interest to researchers. Facebook deleted accounts of companies that violated its

data scraping policies (Nicas 2018).

Such decisions raise important questions about the extent to

which digital platforms can control access to content that users have chosen to make publicly

available.

As interest in extracting insights from digitized text and other forms of digitized content

(e.g., images and videos) grows, researchers should ensure that they have secured the appropriate

permissions to conduct their work. Failure to do so may result in it becoming more difficult to

conduct such projects. One potential solution is the creation of an academic dataset, such as that

made available by Yelp (https://www.yelp.com/dataset), which may contain outdated or

scrubbed data to ensure it does not pose any risk to the company’s operations or user privacy.

The collection and analysis of digitized text, as well as other user-created content, also

raises questions around users’ expectations for privacy. In the wake of GDPR and revelations

Facebook’s terms of service with regards to automated data collection can be found at:

https://www.facebook.com/apps/site_scraping_tos_terms.php

about Cambridge Analytica’s ability to collect user data from Facebook, researchers must be

mindful of the potential abuses of their work. We should also consider the extent to which we are

overstepping the intended use of user-generated content. For example, while a user may

understand that actions taken on Facebook may result in their being targeted with specific

advertisements for brands with which they have interacted, they may not anticipate the totality of

their Facebook and Instagram activity being used to construct psychographic profiles that may be

used by other brands. Understanding consumers’ privacy preferences with regard to their online

behaviors and the text they make available could provide important guidance for practitioners

and researchers alike. Another rich area for future research is the advancement of the precision

with which marketing can be implemented while minimizing the intrusions to privacy (e.g.

Provost et al. 2015).

CONCLUDING THOUGHTS

Communication is an important facet of marketing: communication between

organizations and their partners, between businesses and their consumers, and among consumers.

Textual data holds details of these communications, and through automated textual analysis,

researchers are poised to convert the raw material into valuable insights. Many of the advances in

the use of textual data in recent years were developed in fields outside of marketing. As we look

toward the future and the role of marketers, these recent advancements should serve as

exemplars. Marketers are well positioned at the interface between consumers, firms and

organizations to leverage and advance tools to extract textual information to address some of the

key issues that business and society face today, such as the proliferation of misinformation, the

pervasiveness of technology in our lives, and the role of marketing in society. Marketing offers

an invaluable perspective that is vital to this conversation, but it will only be by taking a boarder

perspective, breaking theoretical and methodological silos, and engaging with other disciplines

that our research can reach its largest possible audience to affect the public discourse. We hope

this framework encourages a reflection on the boundaries that have come to define marketing

and opens avenues for future groundbreaking insights.

REFERENCES

Alessa, Ali and Miad Faezipour (2018), “A Review of Influenza Detection and Prediction

Through Social Networking Sites,” Theoretical Biology and Medical Modelling, 15 (1),

1-27.

Anderson, Eric T. and Duncan I. Simester (2014), “Reviews Without A Purchase: Low Ratings,

Loyal Customers, And Deception," Journal of Marketing Research, 51 (3), 249-269.

Arsel, Zeynep and Jonathan Bean (2013), "Taste Regimes and Market-Mediated

Practice," Journal of Consumer Research, 39, (5), 899–917.

Arvidsson, Adam and Alessandro Caliandro (2016), “Brand Public,” Journal of Consumer

Research, 42 (5), 727-748.

Ashley, Christy and Tracy Tuten (2015), "Creative Strategies in Social Media Marketing: An

Exploratory Study of Branded Social Content and Consumer Engagement," Psychology

& Marketing, 32 (1), 15-27.

Barasch, Alixandra and Jonah Berger (2014), “Broadcasting and Narrowcasting: How Audience

Size Affects What People Share,” Journal of Marketing Research, 51 (3), 286-299.

Bass, Frank M. (1969), "A New Product Growth for Model Consumer Durables," Management

Science, 15(5), 215-227.

Batra, Rajeev and Kevin L. Keller (2016), “Integrating Marketing Communications: New

Findings, New Lessons, and New Ideas,” Journal of Marketing, 80 (6), 122-145.

Berger, Jonah (2014), “Word of Mouth and Interpersonal Communication: A Review and

Directions for Future Research,” Journal of Consumer Psychology, 24 (4), 586-607.

Berger, Jonah and Katherine L. Milkman (2012), “What Makes Online Content Viral?," Journal

of Marketing Research, 49 (2), 192-205.

Berger, Jonah, Yoon Duk Kim, and Robert Meyer (2019a), “Emotional Volatilty and Cultural

Success,” working paper.

Berger, Jonah, Wendy W. Moe and David A. Schweidel (2019b), “What Makes Stories More

Engaging? Continued Reading in Online Content,” working paper.

Berger, Jonah, and Grant Packard (2018), "Are Atypical Things More Popular?," Psychological

Science, 29(7), 1178-1184.

Berman, Ron, Colman Humphrey, Shiri Melumad and Robert J. Meyer (2019), “The Tale of

Two Twitterspheres: Microblogging During and After the 2016 Primary and Presidential

Debates,” Journal of Marketing Research, forthcoming.

Bielby, William and Denise Biebly (1994), "'All Hits Are Flukes': Institutionalized Decision

Making and the Rhetoric of Network Prime-Time Program Development," American

Journal of Sociology, 99(5), 1287-1313.

Blei, David M., Andrew Y. Ng and Michael I. Jordan (2003), “Latent Dirichlet

Allocation,” Journal of Machine Learning Research, 3(Jan), 993-1022.

Boersma, Paul (2001). "Praat, a System for Doing Phonetics by Computer," Glot International 5

(9/10), 341-345.

Bogharti, Reihane and Jonah Berger (2019) “Quantifying 60 Years of Misogyny in Music,”

Working Paper.

Bollen, Johan, Huina Mao and Xiaojun Zeng (2011), “Twitter Mood Predicts the Stock

Market," Journal of Computational Science, 2 (1), 1-8.

Borah, Abhishek, and Gerard J. Tellis (2016), “Halo (spillover) Effects in Social Media: Do

Product Recalls of One Brand Hurt or Help Rival Brands?,” Journal of Marketing

Research, 53 (2), 143-160.

Boyd, Robert and Peter Richerson (1986). Culture and Evolutionary Process. The University of

Chicago Press.

Büschken, Joachim and Greg M. Allenby (2016), "Sentence-based Text Analysis for Customer

Reviews," Marketing Science, 35 (6), 953-975.

Cavalli-Sforza, Luigi Luca, and Marcus W. Feldman. Cultural transmission and evolution: A

quantitative approach. No. 16. Princeton University Press, 1981.

Chen, Zoey and Nicholas H. Lurie (2013), “Temporal Contiguity and Negativity Bias in the

Impact of Online Word of Mouth,” Journal of Marketing Research, 50(4), 463-476.

Chevalier, Judith A. and Dina Mayzlin (2006), “The Effect of Word of Mouth on Sales: Online

Book Reviews,” Journal of Marketing Research, 43 (3), 345-354.

Cohn, M. A., M. R. Mehl, and J. W. Pennebaker (2004), "Linguistic Markers of Psychological

Change Surrounding September 11, 2001," Psychological Science, 15(10), 687–693.

Cook, Thomas D. and Donald Thomas Campbell (1979). Experimental and Quasi-experimental

Designs for Generalized Causal Inference/William R. Shedish, Thomas D. Cook, Donald

T. Campbell. Boston: Houghton Mifflin.

Danescu-Niculescu-Mizil, Christian, Robert West, Dan Jurafsky, Jure Leskovec, and Christopher

Potts (2013), "No Country for Old Members: User Lifecycle and Linguistic Change in

Online Communities," In Proc. of the 22nd Intl. Conf. on World Wide Web, 307–318.

Das, Sanjiv and Mike Y. Chen (2007), "Yahoo! for Amazon: Sentiment Extraction from Small

Talk on the Web," Management Science, 53(9):1375–1388.

Deangelis, Matteo, Andrea Bonezzi, Alessandro M. Peluso, Derek Rucker and Michele Costabile

(2012), "On Braggarts and Gossips: A Self-Enhancement Account of Word-of-Mouth

Generation and Transmission," Journal of Marketing Research, 49. 551-563.

Dichter, E. (1966), "How Word-of-Mouth Advertising Works", Harvard Business Review 44

(Nov-Dec), 147-166.

Dodds, Peter Sheridan, Harris Kameron Decker, Isabel M. Kloumann, Catherine A. Bliss, and

Christopher M. Danforth (2011), “Temporal Patterns of Happiness and Information in a

Global Social Network: Hedonometrics and Twitter,” PLoS ONE, 6(12), e26752.

Dowling, Grahame R. and Boris Kabanoff (1996), “Computer-aided Content Analysis: What Do

240 Advertising Slogans Have in Common?” Marketing Letters, 7 (1), 63-75.

Eliashberg, Jehoshua, Sam K. Hui and Z. John Zhang (2007), “From Story Line to Box Office: A

New Approach for Green-lighting Movie Scripts,” Management Science, 53 (6), 881-893.

Feldman, Ronen, Oded Netzer, Aviv Peretz, and Binyamin Rosenfeld (2015), "Utilizing Text

Mining on Online Medical Forums to Predict Label Change due to Adverse Drug

Reactions." In Proceedings of the 21th ACM SIGKDD international conference on

knowledge discovery and data mining, 1779-1788.

Fiss, Peer C. and Paul M. Hirsch (2005), "The Discourse of Globalization: Framing and

Sensemaking of an Emerging Concept," American Sociological Review, 70 (1), 29–52.

Fossen, Beth L. and David A. Schweidel (2019), “Social TV, Advertising, and Sales: Are Social

Shows Good for Advertisers?,” Marketing Science, 38 (2), 274-295.

Gandomi, Amir and Murtaza Haider (2015), “Beyond the Hype: Big Data Concepts, Methods,

and Analytics,” International Journal of Information Management, 35 (2), 137-144.

Garg, Nikhil, Londa Schiebinger, Dan Jurafsky and James Zou (2018), “Word Embeddings

Quantify 100 years of Gender and Ethnic Stereotypes,” Proceedings of the National

Academy of Sciences, 115 (16), E3635-E3644.

Gebhardt, Gary F., Francis J. Farrelly, and Jodie Conduit (2019). Market Intelligence

Dissemination Practices. Journal of Marketing, 83(3), 72-90.

Ghose, Anindya, and Panagiotis G. Ipeirotis. (2011), “Estimating the Helpfulness and Economic

Impact of Product Reviews: Mining Text and Reviewer Characteristics," IEEE

Transactions on Knowledge and Data Engineering 23 (10), 1498-1512.

Godes, David, and Dina Mayzlin (2004), “Using Online Conversations to Study Word-of-Mouth

Communication," Marketing Science, 23 (4), 545-560.

Godes, David, and José C. Silva (2012), “Sequential and Temporal Dynamics of Online

Opinion," Marketing Science, 31 (3), 448-473.

Goffman, Erving (1959), “The Moral Career of the Mental Patient,” Psychiatry, 22 (2), 123-142.

Gopalan, Prem, Jake M. Hofman and David M. Blei (2013), “Scalable Recommendation with

Poisson Factorization," arXiv preprint arXiv:1311.1704.

Hancock, Jeffrey T., Lauren E. Curry, Saurabh Goorha, and Michael Woodworth (2007), "On

Lying and Being Lied to: A Linguistic Analysis of Deception in Computer-mediated

Communication," Discourse Processes, 45 (1), 1-23.

Hartmann, Jochen, Mark Heitmann, Christina Schamp, and Oded Netzer, (2019), “The Power of

Brand Selfies in Consumer-Generated Brand Images.” Working paper.

Hartmann, Jochen, Juliana Huppertz, Christina Schamp and Mark Heitmann (2018), "Comparing

Automated Text Classification Methods", International Journal of Research in

Marketing, forthcoming.

Hennig-Thurau, Thorsten, Caroline Wiertz and Fabian Feldhaus (2015), “Does Twitter Matter?

The Impact of Microblogging Word of Mouth on Consumers’ Adoption of New Movies,”

Journal of the Academy of Marketing Science, 43 (3), 375-394.

Herhausen, Dennis, Stephan Ludwig, Dhruv Grewal, Jochen Wulf, and Marcus Schögel (2019),

"Detecting, Preventing, and Mitigating Online Firestorms in Brand Communities,"

Journal of Marketing, 83 (3), 1-21.

Hill, Vanessa, and Kathleen M. Carley (1999), "An Approach to Identifying Consensus in a

Subfield: The Case of Organizational Culture," Poetics 27, no. 1, 1-30.

Hirsch, Peer M. (1972) "Processing Fads and Fashions: An Organization-Set Analysis of

Cultural Industry Systems," American Journal of Sociology, 639-659.

Hirsch, Arnold R. (1986) "The Last 'Last Hurrah'," Journal of Urban History, 13(1), 99–110.

Holt, Douglas (2016), "Branding in the Age of Social Media," Harvard Business Review 94, no.

3: 40-50.

Homburg, Christian, Laura Ehm, and Martin Artz (2015), "Measuring and Managing Consumer

Sentiment in an Online Community Environment," Journal of Marketing Research,

52(5), 629-641.

Huang, Karen., Michael Yeomans, Alison W. Brooks, Julia Minson, and Franesca Gino (2017),

"It Doesn’t Hurt to Ask: Question-asking Increases Liking," Journal of Personality and

Social Psychology, 113(3), 430-452.

Humphreys, Ashlee (2010), “Semiotic Structure and the Legitimation of Consumption Practices:

The Case of Casino Gambling,” Journal of Consumer Research, 37 (3), 490-510.

Humphreys, Ashlee, and Kathryn A. LaTour (2013), “Framing the Game: Assessing the Impact

of Cultural Representations on Consumer Perceptions of Legitimacy,” Journal of

Consumer Research, 40 (4), 773-795.

Humphreys, Ashlee, and Rebecca Jen-Hui Wang (2017), “Automated Text Analysis for

Consumer Research,” Journal of Consumer Research, 44 (6), 1274-1306.

Hutto, Clayton J. and Eric Gilbert (2014), “VADER: A Parsimonious Rule-Based Model for

Sentiment Analysis of Social Media Text,” in Eighth international AAAI conference on

weblogs and social media.

Iyengar, Raghuram, Christopher Van den Bulte and Thomas Valente (2011), "Opinion

Leadership and Social Contagion in New Product Diffusion," Marketing Science, 30(2),

195-212.

Jameson, Fredric (2005), Archaeologies of the Future: The Desire Called Utopia and Other

Science Fictions. New York: Verso.

Jurafsky, Dan, Victor Chahuneau, Bryan R. Routledge, and Noah A. Smith (2014), “Narrative

Framing of Consumer Sentiment in Online Restaurant Reviews,” First Monday, 19 (4).

Kanuri, Vamsi. K., Yixing Chen, and Shrihari (Hari) Sridhar. (2018), "Scheduling Content on

Social Media: Theory, Evidence, and Application," Journal of Marketing, 82(6), 89–108.

Kern, Margaret L., Gregory Park, Johannes C. Eichstaedt, H. Andrew Schwartz, Maarten Sap,

Laura K. Smith, and Lyle H. Ungar (2016), "Gaining Insights from Social Media

Language: Methodologies and Challenges," Psychological Methods 21, no. 4: 507.

Kübler, Raoul V., Anatoli Colicev, and Koen Pauwels (2017) "Social Media’s Impact on

Consumer Mindset: When to Use Which Sentiment Extraction Tool." Marketing Science

Institute Working Paper Series 17 (122).

Kulkarni, Dipti (2014), "Exploring Jakobson’s ‘Phatic Function’ in Instant Messaging

Interactions," Discourse & Communication 8, no. 2: 117-136.

LeCun, Yann, Yoshua Bengio and Geoffrey Hinton (2015), “Deep Learning,” Nature, 521

(7553), 436-444.

Lee, Thomas Y. and Eric T. Bradlow (2011), “Automated Marketing Research Using Online

Customer Reviews,” Journal of Marketing Research, 48 (5), 881-894.

Li, Feng and Timon C. Du (2011), “Who Is Talking? An Ontology-based Opinion Leader

Identification Framework for Word-of-Mouth Marketing in Online Social Blogs,”

Decision Support Systems, 51 (1), 190-197.

Liu, Jia and Olivier Toubia (2018), “A Semantic Approach for Estimating Consumer Content

Preferences from Online Search Queries,” Marketing Science, 37 (6), 855-1052.

Liu, Liu , Daria Dzyabura and Natalie Mizik (2018), “Visual Listening In: Extracting Brand

Image Portrayed on Social Media,” working paper.

Liu, Xuan, Savannah Wei Shi, Thales Teixeira, and Michel Wedel (2018), “Video Content

Marketing: The Making of Clips," Journal of Marketing, 82 (4), 86-101.

Ljung, M. (2000), "Newspaper Genres and Newspaper English," In English Media Texts Past

and Present: Language and Textual structure, 131-150.

Longoni, Chiara, Andrea A. Bonezzi and Carey K. Morewedge (2019), “Resistance to Medical

Artificial Intelligence,” Journal of Consumer Research, Forthcoming.

Loughran, Tim and Bill McDonald (2016). “Textual Analysis in Accounting and Finance: A

Survey,” Journal of Accounting Research, 54, 1187-1230.

Ludwig, Stephan, Ko De Ruyter,. Dominik Mahr, Elisabeth C. Bruggen, Martin Wetzels and

Tom De Ruyck (2014), “Take their Word for It: The Symbolic Role of Linguistic Style

Matches in User Communities,” MIS Quarterly, 38 (4), 1201–1217.

Ludwig, Stephan, Ko De Ruyter, Mike Friedman, Elisabeth C. Bruggen, Martin Wetzels, and

Gerard Pfann (2013), “More Than Words: The Influence of Affective Content and

Linguistic Style Matches in Online Reviews on Conversion Rates,” Journal of

Marketing, 77 (1), 87–103.

Ludwig, Stephan, Tom Van Laer, Ko De Ruyter and Mike Friedman (2016), “Untangling a Web

of Lies: Exploring Automated Detection of Seception in Computer-mediated

Communication,” Journal of Management Information Systems, 33(2), 511-541.

Ma, Liye, Sun, Baohung. and Sunder Kekre (2015), “The Squeaky Wheel Gets the Grease—An

empirical analysis of customer voice and firm intervention on Twitter,” Marketing

Science, 34(5), 627-645.

Manchanda, Puneet, Grant Packard and A. Pattabhitamaiah (2015), “Social Dollars: The

Economic Impact of Consumer Participation in a Firm-Sponsored Online Community,”

Marketing Science, 34 (3), 367-387.

Mathwick, Charla, Caroline Wiertz, and Ko De Ruyter (2007), “Social Capital Production in a

Virtual P3 Community," Journal of Consumer Research, 34(6), 832-849.

McCarthy, Daniel and Peter Fader (2018), "Customer-Based Corporate Valuation for Publicly

Traded Non-Contractual Firms," Journal of Marketing Research, 55(5), 617-635.

McCombs, Maxwell E., and Donald L. Shaw (1972), "The Agenda-setting Function of Mass

Media," Public opinion quarterly 36, no. 2: 176-187.

McCracken, G. (1988). Qualitative Research Methods: The Long Interview. Newbury Park, CA:

SAGE Publications, Inc.

McQuarrie, Edward F., Jessica Miller, and Barbara J. Phillips (2012), "The Megaphone Effect:

Taste and Audience in Fashion Blogging," Journal of Consumer Research 40, no. 1: 136-

158.

Melumad, Shiri, J. Jeffrey Inman and Michael Tuan Pham (2019), “Selectively Emotional: How

Smartphone Use Changes User-Generated Content,” Journal of Marketing Research, 56

(2), 259-275.

Mikolov, Tomas, Kai Chen, Greg Corrado, and Jeffrey Dean (2013), “Efficient Estimation of

Word Representations in Vector Space," arXiv preprint arXiv:1301.3781

Moe, Wendy W. and David A. Schweidel (2012), "Online Product Opinions: Incidence,

Evaluation, and Evolution," Marketing Science, 31 (3), 372-386.

Moe, Wendy W. and Michael Trusov (2011), “The Value of Social Dynamics in Online Product

Ratings Forums,” Journal of Marketing Research, 48 (3), 444-456.

Mogilner, Cassie, Sepandar D. Kamvar and Jennifer Aaker (2011), “The Shifting Meaning of

Happiness," Social Psychological and Personality Science, 2 (4), 395-402.

Molner, Sven, Jaideep C. Prabhu and Manjit S. Yadav (2019), “Lost in the Universe of Markets:

Toward a Theory of Market Scoping for Early-Stage Technologies,” Journal of

Marketing, 83 (2), 37-61.

Moody, Christopher E. (2016), “Mixing Dirichlet Topic Models and Word Embeddings to Make

lda2vec,” Research Repository, vol. abs/1605.02019

Moon, Sangkil, and Wagner A. Kamakura (2017), “A Picture is Worth a Thousand Words:

Translating Product Reviews into a Product Positioning Map,” International Journal of

Research in Marketing, 34 (1), 265-285.

Moorman, Christine, Harald J. van Heerde, C. Page Moreau and Robert W. Palmatier (2019a),

“JM as a Marketplace of Ideas,” Journal of Marketing, 83 (1), 1-7.

Moorman, Christine, Harald J. van Heerde, C. Page Moreau and Robert W. Palmatier (2019b),

“Challenging the Boundaries of Marketing,” Journal of Marketing, 83 (5), 1-4.

Muniz Jr., Albert and Thomas O’Guinn (2001), "Brand Community," Journal of Consumer

Research, 27, 412-432.

Narayanan, Sridhar, Ramarao Desiraju and Pradeep K. Chintagunta (2004), “Return on

Investment Implications for Pharmaceutical Promotional Expenditures: The Role of

Marketing-Mix Interactions,” Journal of Marketing, 68 (4), 90-105.

Netzer, Oded, Ronen Feldman, Jacob Goldenberg and Moshe Fresko (2012), “Mine Your Own

Business: Market-structure Surveillance through Text Mining," Marketing Science, 31

(3), 521-543.

Netzer, Oded, Alain Lemaire and Michal Herzenstein (2019), “When Words Sweat: Identifying

Signals for Loan Default in the Text of Loan Applications,” Columbia Business School

Research Paper No. 16-83.

Nicas, Jack (2018), “Facebook Says Russian Firms ‘Scraped’ Data, Some for Facial

Recognition,” The New York Times, October 12, accessed at

https://www.nytimes.com/2018/10/12/technology/facebook-russian-scraping-data.html.

Nisbett, Richard E. and Timothy D. Wilson (1977), “Telling More Than We Can Know: Verbal

Reports on Mental Processes,” Psychological Review, 84 (3), 231-259.

Opoku, Robert, Russell Abratt and Leyland Pitt (2006), “Communicating Brand Personality: Are

the Websites Doing the Talking for the Top South African Business Schools?” Journal of

Brand Management, 14 (1-2), 20-39.

Ott, Myle, Claire Cardie, and Jeff Hancock (2012), "Estimating the Prevalence of Deception in

Online Review Communities," Proc. 21st Internat. Conf. World Wide Web (Association

for Computing Machinery, New York), 201–210.

Packard, Grant, Sarah G. Moore and Brent McFerran (2018), “(I’m) Happy to Help (You): The

Impact of Personal Pronoun Use in Customer-Firm Interactions,” Journal of Marketing

Research, 55 (4), 541-555.

Packard, Grant and Jonah Berger (2019), “How Concrete Language Shapes Customer

Satisfaction,” Working Paper.

Palmatier, Robert W., Rajiv P. Dant and Dhruv Grewal (2007), “A Comparative Longitudinal

Analysis of Theoretical Perspectives of Interorganizational Relationship Performance,”

Journal of Marketing, 71 (4), 172-194.

Peladeau, N (2016), "Wordstat: Content Analysis Module for Simstat," Montreal, Canada:

Provalis Research.

Pennebaker, James W. and Laura A. King (1999), “Linguistic Styles: Language Use as an

Individual Difference,” Journal of Personality and Social Psychology, 77 (6), 1296-1312.

Pennebaker, James W. (2011), "The Secret Life of Pronouns," New Scientist, 211 (2828), 42-45.

Pennebaker, J.W., Booth, R.J., Boyd, R.L., & Francis, M.E. (2015). Linguistic Inquiry and Word

Count: LIWC2015. Austin, TX: Pennebaker Conglomerates (www.LIWC.net).

Pew Research (2018), "Social Media Use in 2018,"

http://www.pewinternet.org/2018/03/01/social-media-use-in-2018/.

Pollach, Irene (2012), “Taming Textual Data: The Contribution of Corpus Linguistics to

Computer-aided Text Analysis,” Organizational Research Methods, 15 (2), 263-287.

Provost, Foster, Brian Dalessandro , Rod Hook, Xiaohan Zhang, Alan Murray (2009), "Audience

Selection for On-line Brand Advertising: Privacy-friendly Social Network

Targeting," Proc. 15th ACM SIGKDD Internat. Conf. Knowledge Discovery Data

Mining (ACM, New York), 707–716.

Puranam, Dinesh, Vishal Narayan and Vrinda Kadiyali (2017), “The Effect of Calorie Posting

Regulation on Consumer Opinion: A Flexible Latent Dirichlet Allocation Model with

Informative Priors,” Marketing Science, 36 (5), 726-746.

Ransbotham, Sam, Nicholas Lurie and Hongju Liu. (2019), "Creation and Consumption of

Mobile Word of Mouth: How Are Mobile Reviews Different?," Marketing Science,

fortcoming.

Reagan Andrew J., Lewis Mitchell, Dilan Kiley, Christopher M. Danforth and Petter Sheridan

Dodds (2016), “The Emotional Arcs of Stories are Dominated by Six Basic Shapes,” EPJ

Data Science, 5 (1), 1-12.

Rocklage, Matthew D., and Russell H. Fazio (2015), “The Evaluative Lexicon: Adjective use as

a means of assessing and distinguishing attitude valence, extremity, and emotionality,”

Journal of Experimental Social Psychology 56, 214-227.

Rocklage, Matthew D., Derek D. Rucker, and Loran F. Nordgren (2018), “The Evaluative

Lexicon 2.0: The Measurement of Emotionality, Extremity, and Valence in Language,”

Behavior Research Methods, 50, 1327-44.

Rodriguez, Salvador (2017), “U.S. Judge Says LinkedIn Cannot Block Startup from Public

Profile Data,” Reuters, August 14, accessed at https://www.reuters.com/article/us-

microsoft-linkedin-ruling-

idUSKCN1AU2BV?feedType=RSS&feedName=technologyNews.

Rogers, E.M. (1995). Diffusion of Innovations. 4th Edition. The Free Press. New York.

Rosa, Jose Antonio, Joseph F. Porac, Jelena Runser-Spanjol, Michael S. Saxon (1999),

"Sociocognitive Dynamics in a Product Market", Journal of Marketing, 63, 64-77.

Rude, Stephanie, Eva-Maria Gortner and James Pennebaker (2004), “Language Use of

Depressed and Depression-Vulnerable College Students,” Cognition & Emotion, 18 (8),

1121-1133.

Salganik, Matthew J., Peter Dodds and Duncan Watts. (2006), "Experimental Study of Inequality

and Unpredictability in an Artificial Cultural Market," Science (New York, N.Y.). 311.

854-6.

Scaraboto, Daiane and Eileen Fischer, (2012), "Frustrated Fashionistas: An Institutional Theory

Perspective on Consumer Quests for Greater Choice in Mainstream Markets," Journal of

Consumer Research 39, no. 6: 1234-1257.

Schoenmüller, Verena, Oded Netzer, and Florian Stahl (2019), “The Extreme Distribution of

Online Reviews: Prevalence, Drivers and Implications,” Columbia Business School

Research Paper.

Schweidel, David A. and Wendy W. Moe (2014), “Listening in on Social Media: A Joint Model

of Sentiment and Venue Format Choice,” Journal of Marketing Research, 51 (4), 387-

402.

Searle, John (1976), “A Classification of Illocutionary Acts,” Language in Society, 5 (1), 1–23.

Simonton, Dean Keith (1980), "Thematic Fame, Melodic Originality, and Musical zeitgeist: A

Biographical and Transhistorical Content Analysis," Journal of Personality and Social

Psychology, 38. 972-983.

Snefjella, Bryor and Victor Kuperman (2015), “Concreteness and psychological distance in

natural language use,” Psychological science, 26(9), 1449-1460.

Srivastava, Sameer B. and Amir Goldberg (2017), “Language as a Window into Culture,”

California Managmeent Review, 60 (1), 56-69.

Stewart, D.W. and D.H. Furse (1986), TV Advertising: A Study of 1000 Commercials, MA:

Lexington Books.

Tausczik, Yla R. and James.W. Pennebaker (2010), “The Psychological Meaning of words:

LIWC and Computerized Text Analysis Methods,” Journal of Language and Social

Psychology, 29 (1) , 24-54.

Tellis, Gerard J., Deborah J. MacInnis, Seshadri Tirunillai and Yanwei Zhang (2019), “What

Drives Virality (Sharing) of Online Digital Content? The Critical Role of Information,

Emotion, and Brand Prominence,” Journal of Marketing, 83 (4), 1-20.

Thompson, Craig J., and Gokcen Coskuner-Balli (2007), "Countervailing Market Responses to

Corporate Co-optation and the Ideological Recruitment of Consumption

Communities," Journal of Consumer Research 34, no. 2: 135-152.

Timoshenko, Artem and John R. Hauser (2019), “Identifying Customer Needs from User-

Generated Content,” Marketing Science, Forthcoming.

Tirunillai, Seshadri and Gerard J. Tellis (2012), “Does Chatter Really Matter? Dynamics of

User-Generated Content and Stock Performance,” Marketing Science, 31 (2), 198-215.

Tirunillai, Seshadri, and Gerard J. Tellis (2014), “Mining Marketing Meaning from Online

Chatter: Strategic Brand Analysis of Big Data Using Latent Dirichlet

Allocation,” Journal of Marketing Research, 51 (4), 463-479.

Toubia, Olivier, Garud Iyengar, Renée Bunnell, and Alain Lemaire (2018), “Extracting Features

of Entertainment Products: A Guided LDA Approach Informed by the Psychology of

Media Consumption," Journal of Marketing Research, forthcoming.

Toubia, Olivier and Oded Netzer (2017), “Idea Generation, Creativity, and Prototypicality,”

Marketing Science, 36 (1), 1-20.

Tsai, Jeanne L. (2007), “Ideal Affect: Cultural Causes and Behavioral Consequences,”

Perspectives on Psychological Science, 2 (3), 242-259.

Van Laer, Tom, Jennifer Edson Escalas, Stephan Ludwig, and Ellis A. Van den Hende (2018),

“What Happens in Vegas Stays on TripAdvisor? Computerized Analysis of Narrativity in

Online Consumer Reviews,” Journal of Consumer Research, Forthcoming.

Van Zant, Alex B. and Jonah Berger (2019), “How the Voice Persuades,” Rutgers Working

Paper.

Villaroel Ordenes, Francisco, Dhruv Grewal, Stephan Ludwig, Ko De Ruyter, Dominik Mahr,

Martin Wetzels, and Praveen Kopalle (2018), "Cutting through Content Clutter: How

Speech and Image Acts Drive Consumer Sharing of Social Media Brand Messages,"

Journal of Consumer Research, 45 (5) 988–1012.

Villaroel Ordenes, F., Francisco, Stephan Ludwig, Ko De Ruyter, Dhruv Grewal, and Martin

Wetzels (2017), "Unveiling What is Written in the Stars: Analyzing Explicit, Implicit,

and Discourse Patterns of Sentiment in Social Media," Journal of Consumer Research,

43(6), 875-894.

Vosoughi, Soroush, Deb Roy and Sinan Aral (2018), “The Spread of True and False News

Online,” Science, 359 (6380), 1146-1151.

Wang, Xin, Feng Mai, and Roger HL Chiang (2013), “Database Submission—Market Dynamics

and User-Generated Content about Tablet Computers,” Marketing Science, 33 (3), 449-

458.

Wang, Yanwen, Michael Lewis and David A. Schweidel (2018), “A Border Strategy Analysis of

Ad Source and Message Tone in Senatorial Campaigns,” Marketing Science, 37 (3), 333-

355.

Weber, Klaus (2005), “A Toolkit for Analyzing Corporate Cultural Toolkits,” Poetics, 33 (3-4),

227-252

Wies, Simone, Arvid Oskar Ivar Hoffmann, Jaako Aspara and Joost ME Pennings (2019), “Can

Advertising Investments Counter the Negative Impact of Shareholder Complaints on

Firm Value?” Journal of Marketing, 83 (4), 58-80.

Xiao, Li, Hye-Jin Kim, and Min Ding. (2013), "An Introduction to Audio and Visual Research

and Applications in Marketing," Review of Marketing Research, 10, 213-253.

Xiong, Ying, Moonhee Cho, and Brandon Boatwright (2019), "Hashtag Activism and Message

Frames among Social Movement Organizations: Semantic Network Analysis and

Thematic Analysis of Twitter During The #MeToo movement," Public Relations

Review 45, no. 1: 10-23.

Yadav, Manjit S., Jaideep C. Prabhu, and Rajesh K. Chandy (2007), “Managing the Future: CEO

Attention and Innovation Outcomes,” Journal of Marketing 71 (4), 84-101.

Ying, Yuanping, Fred Feinberg and Michel Wedel (2006), "Leveraging Missing Ratings to

Improve Online Recommendation Systems," Journal of Marketing Research, 43 (3), 355-

365.

Zhong, Ning and David A. Schweidel (2019), “Capturing Changes in Social Media Content: A

Multiple Latent Changepoint Topic Model,” Emory University, working paper.

Table 1: Text Producers and Receivers

Text Producers

Text Receivers

Consumers

Firms

Investors

Institutions/Society

Consumers

• Online Reviews (Lee and Bradlow 2011; Chen and

Lurie 2013; Kronrod and Danziger 2013; Anderson

and Simester 2014; Fazio and Rockledge 2015;

Puranam et al. 2017; Moon and Kamakura 2017;

Melumad et al. 2019; Liu et al., 2019)

• Social Media (Netzer, et al., 2012; Villaroel 2017;

Hamilton, Schlosser and Chen 2017)

• Offline word of mouth (Mehl and Pennebaker 2003,

Berger and Schwartz 2011)

• Forms and applications

(Netzer et al. 2019)

• Idea generation contexts

(Toubia and Netzer 2017;

Bayus 2013)

• Social media/brand

communities (Herhausen et

al 2019)

• Consumer complaints (Ma et

al. 2015,)

• Customer language on

service calls

• Tweeting at companies (Liu,

et al. 2016)

• Stock market reactions

to consumer text

(Bollen, et al. 2011;

Tirunillai and Tellis

2012)

• Protests

• Petitions

• Societal reactions to political events,

speeches, etc. (Berman, et al. 2019)

• Crowdsourcing knowledge (Ramsbotham,

Kane and Lurie 2012)

• Letters to the Editor

• Online comments section

• Public comments (e.g., FCC hearing on

net neutrality)

• Activism (e.g., organizing political

movements and marches)

Firms

• Owned media (e.g., company website and social

media, Villaroel, Ordenes et al. 2018)

• Advertisements (Stewart and Furse 1986, Rosa et al.

1999; Liaukonyte et al. 2015; Fossen and Schweidel

2017, 2019)

• Customer service agents (Packard, Moore, and

McFerran 2018; Packard and Berger 2019)

• Packaging, including labels

• Text used in instructions

• Trade Publications (Weber et

al 2008),

• Inter-firm communication

emails (Ludwig, et al 2016)

• Whitepapers

• Financial reports

(Loughran and

McDonald 2016)

• Corporate

communications

(Hobson et al. 2012)

• CEO letters to

shareholders (Yadav et

al. 2007

• Editorials by firm stakeholders

• Interviews with business leaders

Investors

• Shareholder feedback,

meeting memoranda (Wies

et al 2019; Yadav et al.

2007).

• Sector Reports

Institutions/

Society

• News content (Humphreys 2010; Berger and Milkman

2012; Berger et al. 2019a)

• Movies (Eliashberg, et al. 2007, 2014; Reagan et al.

2016; Berger, et al. 2019b; Toubia et al 2019)

• Songs (Berger and Packard 2018; Packard and Berger

2019)

• Books (Akpinar and Berger 2015; Sorescu et al. 2018)

• Business section

• Specialty magazines (e.g.

Wired, HBR)

• WSJ

• Fortune

• Various forms of

investment advice that

come from media

• Government documents, hearings, and

memoranda (Chappell et al 1997)

• Forms of public dialogue or debate

Table 2: The Text Analysis Workflow

Data Pre-Processing

Common Tools

Measurement

Validity

• Data acquisition: Obtain or

download (often in an HTML

format) text.

• Tokenization: Break text into

units (often words and

sentences) using delimiters

(e.g., periods).

• Cleaning: Remove non-

meaningful text (e.g., HTML

tags) and non-textual

information.

• Removing stop words:

Eliminate common words such

as “a” or “the” that appear in

most documents.

• Spelling: Correct spelling

mistakes using common

spellers.

• Stemming and

Lemmatization:Reduce words

into their common stem or

lemma.

• Entity extraction: Tools used to

extract the meaning of one word

at a time or simple co-

occurrence of words. These

tools include dictionaries, part

of speech classifiers, many

sentiment analysis tools and for

complex entities machine

learning tools.

• Topic modeling: Topic

modeling can identify the

general topics (described as a

combination of words) that are

discussed in a body of text.

Common tools include Latent

Dirichlet Allocation and

Poisson Factorization.

• Relation extraction: Going

beyond entity extraction, the

researcher may be interested in

identifying textual relationships

among extracted entities.

Relation extraction often

requires the use of supervised

machine learning approaches.

• Count measures: Set of

measures used to represent the

text as count measures. The tf-

idf measure allows to control

for the popularity of the word

and the length of the

document.

• Similarity measures: Cosine

similarity and the Jaccard

index are often used to

measure the similarity of the

text between documents.

• Accuracy measures: Often

used relative to human-coded

or externally0validated

documents the measures of

recall, precision, F1, and the

area under the curve (AUC) of

the receiver operating

characteristic (ROC) curve are

often used.

• Readability measures:

Measure such as the Simple

Measure of Gobbledygook

(SMOG) are sued to assess the

readability level of the text.

• Internal Validity

- Construct: Dictionary

validation and sampling and

saturation procedures to ensure

constructs are correctly

operationalized in text.

- Concurrent: Compare

operationalizations with prior

literature.

- Convergent: Multiple

operationalizations of key

constructs.

- Causal: Control for factors

related to alternative

hypotheses.

External Validity

- Predictive: Use conclusions to

predict key outcome variable

(e.g. sales, stock price).

- Generalizability: Replicate

effects in other domains.

- Robustness: Test conclusions

on hold out samples (k-fold);

compare different categories

within the dataset.

Table 3: Data Pre-Processing steps

Data Processing Atep

Issues to Consider

Illustration

Data acquisition

• Is the data readily available in textual

format or does the research needs to use

a web scrapper to find the data?

• What are the legal guidelines for using

the data (particularly relevant for Web

scrapped data)?

Tweets mentioning different

brands from the same category

during a particular timeframe

are downloaded from Twitter.

Tokenization

• What is the unit of analysis (word,

sentence, thread, paragraph)?

• Use smart tokenization for delimiters and

adjust to specific unique delimiters found

in the corpora.

The unit of analysis is the

individual tweet. The words in

the tweet are the tokens of the

document.

Cleaning

• Web scraped data often requires cleaning

of HTML tags and other symbols.

• Depending on the research objective

certain textual features (e.g., advertising

on the page) may or may not be cleaned.

• Expand of contractions such as “isn’t” to

“is not”.

URLs are removed and

emojis/emoticons are converted

to words.

Removing stop word

• Use a stop word list available by the text

mining software but adapt it to your

specific application by adding/removing

relevant stop words.

• If the goal of the analysis is extracting

writing style it is advisable to keep

all/some of the stop words.

Common words are removed.

The remaining text contains

brand names, nouns, verbs,

adjectives and adverbs.

Spelling

• Can use commonly used spellers in text-

mining packages (e.g., the Enchant

speller).

• Language that is specific to the domain

may be erroneously coded as a spelling

mistake.

• May wish to record the number of

spelling mistakes as an additional textual

measure.

Spelling mistakes removed,

enabling analysis into consumer

perceptions (manifest through

word choice) of different

brands.

Stemming and

Lemmatization

• Can use commonly used stemmers in

text-mining packages (e.g., Porter

stemmer).

• If the goal of the analysis is extracting

writing style stemming can mask the

tense used.

Verbs and nouns are

“standardized” by reducing to

their stem or lemma.

Table 4: Taxonomy of Text Analysis Tools

Approach

Common Tools

Research Questions

Benefits

Limitations and Complexities

Marketing Examples

Entity (word)

extraction:

Extracting and

identifying a

single word/n-

gram

• Named Entity Extraction

(NER) tools (e.g., Stanford

NER)

• Dictionaries and lexicons

(e.g., LIWC, EL 2.0,

SentiStrength, Vader)

• Rule-based classification

• Linguistic-based NLP

tools

• Machine learning

classification tools

(conditional Random

fields, hidden Markov

models, deep learning)

• Brand buzz monitoring

• Predictive models where text is

an input

• Extracting psychological states

and traits

• Sentiment Analysis

• Consumer and market trends

• Product recommendations

• Can extract a large

number of entities

• Can uncover known

entities such as

people, brands,

locations

• Can be combined

with dictionaries to

extract sentiment or

linguistic styles

• Relatively simple to

use

• Can be unwieldy due to the large

number of entities extracted

• Some entities that have multiple

meaning are difficult to extract

(e.g., the laundry detergent brand

“all”)

• Slang and abbreviations make

entity extraction more difficult in

social media

• Machine learning tools may

require large human coded

training data

• Can be limited for sentiment

analysis

• Lee and Bradlow (2011)

• Berger and Milkman (2011)

• Ghose et al. (2012)

• Tirunillai and Tellis (2012)

• Humphreys and Thompson (2014)

• Berger et al. (2018)

• Packard et al. (2018)

Topic

extraction:

Extracting the

topic discussed in

the text

• Latent Semantic Analysis

(LSA)

• Latent Dirichlet Allocation

(LDA)

• Poisson Factorization (PF)

• LDA2vec - Word

embedding

• Summarizing the discussion

• Identifying consumer and

market trends

• Identifying customer needs

• Topics often provide

useful summarization

of the data

• Data reduction

permits the use of

traditional statistical

methods in

subsequent analysis

• Easier to assess

dynamics

• The interpretation of the topics

can be challenging

• No clear guidance on the

selection of the number of topics

• Can be difficult with short text

(e.g., Tweets)

• Tirunillai and Tellis (2014)

• Buschken and Allenby (2016)

• Puranam et al. (2017)

• Berger and Packard (2018)

• Liu and Toubia (2018)

• Toubia et al. (2018)

• Zhong and Schweidel (2019)

• Ansari, Li and Yang (2018)

• Timoshenko and Hauser (2019)

• Liu et al. (2016, 2019)

Relation

extraction:

Extracting and

identifying

relationships

among words

• Co-occurrence of entities

• Hand-written rule

• Supervised machine

learning

• Deep learning

• Word2vec - Word

embedding

• Stanford Sentence and

Grammatical Dependency

Parser

• Market mapping

• Identifying problems

mentioned with specific

product features

• Identifying sentiment for a

focal entity

• Which attributes of a product

are mentioned

positively/negatively?

• Identifying events and

consequences (e.g., crisis) from

consumer or firm generated text

• Managing service relationships

• Relaxing the “bag-of-

words” assumption of

most text mining

methods

• Relating the text to a

particular focal entity

• Advances in text

mining methods will

offer new

opportunities in

marketing

• Accuracy of current approaches

is limited

• Complex relationships may be

difficult to extract

• It is advised to develop domain-

specific sentiment tools as

sentiment signals can vary from

one domain to another

• Netzer et al. (2012)

• Toubia and Netzer (2017)

• Boghrati and Berger (2019)

Table 5: Text Analysis Validation Techniques

Type of

Validity

Validation

Technique

Description of Method for Validation

References

Internal Validity

Construct

Validity

Dictionary

validation

After draft dictionary is created, pull 10% of the

sample and calculate the hit rate. Measures such

hit rates, precision and recall can be used to

measure accuracy.

Weber 2005

Have survey participants rate words included in

the dictionary. Based on this data, dictionary can

also be weighted to reflect the survey data.

Brysbaert et al 2014

Have 3 coders evaluate the dictionary categories.

If 2 of the 3 coders agree the word is part of the

category, include; if not exclude. Calculate overall

agreement.

Pennebaker 2001;

Humphreys 2010

Saturation

Pull 10% of instances coded from the data and

calculate the hit rate. Adjust wordlist until

saturation reaches 80% hit rate

Weber 2005

Concurrent

Validity

Multiple

Dictionaries

Calculate and compare multiple textual measures

of the same construct (e.g. multiple sentiment

measures)

Hartmann et al 2018

Comparison of

Topics

Compare with other topic models of similar

datasets in other research (e.g. hotel reviews)

Mankad et al 2016

Convergent

Validity

Triangulation

Look within text data for converging patterns (e.g.

positive/e emotion correlates with known-positive

attributes); apply Principle Components Analysis

to show convergent groupings of words

Humphreys 2010;

Kern et al 2016

Multiple

Operationalization

Operationalize construct with textual and non-

textual data (e.g. sentiment and star rating)

Mudambi et al 2014;

Ghose et al 2012

Causal Validity

Control Variables

Include variables in the model that address rival

hypotheses to control for these effects

Ludwig et al 2013

Laboratory Study

Replicate focal relationship between the IV and

DV in a laboratory setting

Spiller and

Belogolova 2016;

van Laer et al 2018

External Validity

Generalizability

Replication with

different datasets

Compare the results from the text analysis with the

results obtained other (possibly non-text related)

datasets

Netzer et al 2012

Predict key

performance

measure

Include results from text analysis in regression or

other model to predict a key outcome (e.g. sales,

engagement)

Fossen and

Schweidel 2019

Predictive

Validity

Hold out sample

Train model on approximately 80%-90% of the

data and validate the model with the remaining

data. Validation can be done using k-fold

validation, which trains the mode on k-1 subsets

of the data and predicts for the remaining subset of

testing.

Jurafsky et al 2014

Robustness

Different statistical

measures,

unitizations

Use different, but comparable, statistical measures

or algorithm (e.g. lift, cosine similarity, Jaccard

similarity), aggregate at different levels (e.g. day,

month)

Netzer et al 2012

WEB APPENDIX: ADDITIONAL REFERENCES

Akpinar, Ezgi and Jonah Berger (2015), “Drivers of Cultural Success: The Case of Sensory

Metaphors,” Journal of Personality and Social Psychology, 109 (1), 20-34.

Ansari, Asim, Yang Li, and Jonathan Z. Zhang (2018), "Probabilistic Topic Model for Hybrid

Recommender Systems: A Stochastic Variational Bayesian Approach," Marketing

Science, 37 (6), 987-1008.

Bayus, Barry (2013), “Crowdsourcing New Product Ideas over Time: An Analysis of the Dell

IdeaStorm Community", Management Science, 59 (1), 226-244.

Berger, J. and E.M. Schwartz (2011), “What Drives Immediate and Ongoing Word of Mouth?”

Journal of Marketing Research, 48(5), 869-880.

Brysbaert, M., A.B. Warriner and V. Kuperman (2014), “Concreteness Ratings for 40 Thousand

Generally Known English Word Lemmas,” Behavior research methods, 46(3), 904-911.

Chappell, H. W. J., et al. (1997), "Monetary Policy Preferences of Individual FOMC Members:

A Content Analysis of the Memoranda of Discussion," The Review of Economics and

Statistics 79(3): 454-460.

Fossen, Beth L. and David A. Schweidel (2017), “Television Advertising and Online Word-of-

Mouth: An Empirical Investiation of Social TV Activity,” Marketing Science, 36 (1),

105-123.

Hobson, Jessen L., William J. Mayew and Mohan Venkatachalam (2012), “Analyzing Ppeech to

Detect Financial Misreporting," Journal of Accounting Research, 50 (2), 349-392.

Hamilton, R.W., A. Schlosser, A. and Y.J. Chen (2017), “Who's Driving this Conversation?

Systematic Biases in the Content of Online Consumer Discussions,” Journal of

Marketing Research, 54(4), 540-555.

Humphreys, Ashlee, and Craig J. Thompson (2014), “Branding Disaster: Reestablishing Trust

through the Ideological Containment of Systemic Risk Anxieties,” Journal of Consumer

Research, 41 (4): 877-910.

Kronrod, Ann and Shai Danziger (2013), “Wii Will Rock You!” The Use and Effect of

Figurative Language in Consumer Reviews of Hedonic and Utilitarian Consumption.

Journal of Consumer Research, 40(4), 726-739.

Liaukonyte, Jura, Thales Teixeira and Kenneth C. Wilbur (2015), "Television Advertising and

Online Shopping," Marketing Science, 34 (3), 311-330.

Liu, Xaio, Dokyun Lee, and Kannan Srinivasan (2019) “Large Scale Cross-Category Analysis of

Consumer Review Content and Sales Conversion Leveraging Deep Learning,” Journal of

Marketing Research, Forthcoming.

Liu, Xiao, Param Vir Singh, and Kannan Srinivasan (2016), “A Structured Analysis of

Unstructured Big Data Leveraging Cloud Computing,”, Marketing Science, Vol. 35 No.3,

May-June 2016, pp. 363-388.

Mankad, S., H.S. Han, J. Goh and S. Gavirneni (2016), “Understanding Online Hotel Reviews

through Automated Text Analysis,” Service Science, 8(2), 124-138.

Mehl, M.R. and J.W. Pennebaker (2003), “The Sounds of Social Life: A Psychometric Analysis

of Students' Daily Social Environments and Natural Conversations,” Journal of

personality and social psychology, 84(4), 857-870.

Mudambi, S.M., D. Schuff and Z. Zhang (2014), “Why aren't the stars aligned? An analysis of

online review content and star ratings,” In 2014 47th Hawaii International Conference on

System Sciences (pp. 3139-3147). IEEE.

Pennebaker, James W., Martha E Francis, and Roger J. Booth (2001), "Linguistic Inquiry and

Word Count: Liwc 2001," Mahway: Lawrence Erlbaum Associates, 71, 2001.

Sorescu, Alina., Sorin M. Sorescu, Will J. Armstrong and Bart Devoldere (2018), “Two

Centuries of Innovations and Stock Market Bubbles,” Marketing Science, 37(4), 507-529.

Spiller, Stephen A. and L. Belogolova (2016), “On Consumer Beliefs about Quality and Taste,”

Journal of Consumer Research, 43(6), 970-991.

Weber, Klaus, Kathryn Heinze, K.L. and Michaela DeSoucey (2008), “Forage for Thought:

Mobilizing Codes in the Movement for Grass-fed Meat and Dairy

products,” Administrative Science Quarterly, 53(3), 529-567.

WEB APPENDIX

Textual Constructs Commonly Measured in Marketing

Marketing

Construct

Definition

Marketing Examples

Related Research

Using Scales

Consumer

Sentiment

Positive, negative or neutral

attitudes toward an idea,

product, company, brand, or

practice

Villaroel Ordenes et al. 2017;

Schweidel and Moe 2014; Büschken

and Allenby, 2016; Homburg et al.

2015; Herhausen et al. 2019;

Sonnier, McAlister and Rutz 2011;

Tirunillai and Tellis 2012; Rogers, et

al. 2017; Nguyen and Chaudhuri

2018; Ludwig et al. 2013

Authenticity

a socially-ascribed perception

that an idea, object, place, or

practice is "real" or "genuine"

Kovacs et al 2015

Satisfaction

an affective response to or

evaluation of a product

acquisition and/or consumption

experience

Ma et al. 2015

Fornell et al 1996

Emotion

Mogilner et al. 2011; Berger and

Heath 2006; Barasch and Berger

2014; Heimbach and Hinz 2016; Yin

et al. 2017; Del Vicario et al 2016;

Berger and Packard 2018; Fazio and

Rockledge 2015

Narrativity

a storyteller’s account of an

event or a sequence of events

leading to a transition from an

initial state to a later state or

outcome

van Laer et al. 2019

van Laer et al. 2014

Needs

"an abstract context-dependent

statement describing the

benefits... that the customer

Timoshenko and Hauser 2019

seeks to obtain from a product or

service"

Creativity

"the forming of associative

elements into new combinations

which either

meet specified requirements or

are in some way useful.”"

Toubia and Netzer 2017

Firm

Gdvertising

goals

brands' intentions when tweeting

(i.e. to inform, excite or direct)

Villaroel Ordenes et al. 2018

Future

Orientation

The use of future words by

CEOs

Yadav, Prabhu, and Chandy 2007

Deceitful

Intentions

expressions indicative of

deceitful intend

Ludwig et al. 2016

Economic vs.

relational

focus

firm orientation toward

economic or relational objectives

Kim and Kumar 2018

Brand

Personality

"the set of

human characteristics associated

with"

Okopu et al 2006

Aaker 1997

Strategic

orientation

"the organizationwide generation

of market intelligence pertaining

to current and future customer

needs, dissemination of the

intelligence across departments,

and organizationwide

responsiveness to it."

Noble, Sinha, and Kumar 2002;

Molner et al. 2019

Jaworski and Kohli

1993; Kirca,

Jayachandran, and

Bearden 2005

Culture

Legitimacy

Congruence with current

regulations, norms, and cultural-

cognitive structures in a society

Humphreys 2010

Elsbach 1994

Political

ideology

a deeply-held set of values or

beliefs that structure to an

individual's view on a range of

issues

Daniel Diermeier, Jean-François

Godbout, Bei Yu and Stefan

Kaufmann 2011

Institutional

logics

"the socially constructed patterns

of symbols and material

practices, assumptions, values,

beliefs, and rules by which

individuals and organizations

produce and reproduce their

material subsistence, organize

time and space, and provide

meaning to their social reality"

(Ocasio and Thornton 1999, p.

804)

Ertimur and Coskuner-Balli 2015