Exhibit 3 — Brooks v. Thomson Reuters Corporation (Dkt. 159.5)

Record facts

U.S. District Court for the Northern District of California · No. 3:21-cv-01418-EMC · Doc. 159-5 · 2023-02-06 · Docket on CourtListener

Full text

EXHIBIT 3 
 
 
 
 
Case 3:21-cv-01418-EMC     Document 159-5     Filed 02/06/23     Page 1 of 7

Using Big Data as a window into consumers’ psychology
Sandra C Matz1 and Oded Netzer2
The rise of ‘Big Data’ had a big impact on marketing research
and practice. In this article, we first highlight sources of useful
consumer information that are now available at large scale and
very little or no cost. We subsequently discuss how this
information – with the help of new analytical techniques – can
be translated into valuable insights on consumers’
psychological states and traits that can, in turn, be used to
inform marketing strategy. Finally, we discuss opportunities
and challenges related to the use of Big Data as a window into
consumers’ psychology, and provide recommendations for
how to implement related technologies in a way that benefits
both businesses and consumers.
Addresses
1 University of Cambridge, Department of Psychology, Downing Site,
Cambridge CB2 3EB, United Kingdom
2 Columbia Business School, Columbia University, New York,
United States
Corresponding author: Matz, Sandra C (sm917@cam.ac.uk)
Current Opinion in Behavioral Sciences 2017, 18:7–12
This review comes from a themed issue on Big data in the
behavioural sciences
Edited by Michal Kosinski and Tara Behrend
http://dx.doi.org/10.1016/j.cobeha.2017.05.009
2352-1546/ã 2017 Elsevier Ltd. All rights reserved.
The availability of data at large volume, variety, velocity
and veracity, often termed as ‘Big Data’, had a big impact
on marketing research [1

] and practice [2

]. The wealth
of personal information available about consumers online
makes it possible to understand and cater to the individ-
ual needs of consumers better than ever before. Whether
it is their Spotify playlists, Facebook profile, Google
search queries, or mobile location, the digital footprints
consumers leave with every step they take in the digital
environment create extensive records of their personal
habits and preferences. By tapping into this rich pool of
consumer data, businesses can enhance consumers’ expe-
rience by better matching the marketing offering to
consumers’ preferences and do so at the appropriate
moment.
Applications of Big Data in marketing have largely
focused on (a) assessing customers’ preferences [e.g.,3],
(b) predicting what customers are most likely to buy next
[e.g.,4–6], (c) improving targeted advertising [e.g.,7

,8],
(d) understanding brand perceptions [e.g.,9,10], and (e)
describing the competitive landscape [e.g.,11]. See Wedel
and Kannan [1

] for a review. However, investigations of
how Big Data can help inform some of the more psycho-
logical aspects of consumer behavior that is aimed at
understanding – rather than merely predicting – con-
sumer attitudes and emotions has thus far only received
scant attention. Davenport et al. [12] (2001, p. 63) note
that holding vast amounts of customer data might help
businesses to ‘know more about their customers’ but does
not necessarily allow them to ‘know the customers
themselves’. The focus of this paper is to highlight the
existing work and discuss the potential of using Big Data
as a means to better understand consumers’ stable psy-
chological traits as well as more malleable psychological
states.
New sources of consumer information
Traditional approaches to gathering ‘human-centric’ con-
sumer information include extensive customer surveys,
focus groups, interviews, observation studies and limited
scope secondary data such as scanner panel data [1

]. For
example, as part of the Nordstrom’s Personal Touch
program, personal shoppers recorded detailed informa-
tion on customers likes and dislikes, their lifestyle and
tastes through telephone and face-to-face conversations
as well as observations made in the store [12]. While the
outlined approaches can generate valuable customer
knowledge, they are not only expensive and time-con-
suming – and therefore difficult to scale – but also prone
to numerous well established response biases [13]. For
example, even the most motivated customer will find it
difficult to accurately recall the purchases they made over
the past four weeks or the exact feeling they experienced
when purchasing a specific product.
Thanks to technological advances in the collection, stor-
age and analysis of large amounts of data, businesses can
now gain valid insights on millions of consumers by
looking at the digital records that are passively collected
as consumers go about their daily lives. In fact, observing
the behavior of a consumer in a traditional retail store is
very similar to analyzing the journey of a customer who is
browsing a company’s online store (e.g., one can examine
the characteristics of products the user has looked at and/
or bought, measure the time they took to make a decision,
or implement mouse-tracking technologies to study the
decision process). Similarly, customer forums, product
Available online at www.sciencedirect.com
ScienceDirect
www.sciencedirect.com 
Current Opinion in Behavioral Sciences 2017, 18:7–12
Case 3:21-cv-01418-EMC     Document 159-5     Filed 02/06/23     Page 2 of 7

reviews and posts in social media make it possible to
observe large and natural ‘focus groups’ at very little to no
cost [11].
The sources of information businesses can tap into to
learn more about their consumers are almost limitless, and
it would go beyond the scope of this paper to discuss all of
them in detail (for an overview see Wedel and Kannan
[1

], Fig. 2). Among the most vital ones are historical
purchasing data, credit card records, search queries,
browsing histories, blog posts, social media profiles, and
smartphone sensor data (e.g., GPS location). Importantly,
it is often possible to combine the information extracted
from different sources to form a more holistic picture of a
consumer’s daily habits and preferences. By integrating
information obtained from a consumer’s social media
profile, their phone logs and sensor data as well as their
credit card spending, for example, one can get a fairly
accurate picture of what a consumer has done when and
with whom.
These new sources of data not only come from various
sources, but they also come in multiple formats. While
traditional data have been primarily structured in a
numeric format, social media data, are primarily unstruc-
tured including, text, images, audio and video. Accord-
ingly, different analytical approaches are needed to con-
vert such data into knowledge and insights.
Turning Big Data into human-centric
customer knowledge
The task of turning vast amounts of – often unstructured
– data into insightful consumer knowledge is not easy and
often requires the application of analytical techniques
that are outside of the standard methodological tool box of
consumer behavior researchers [14]. However, recent
years have seen the rise of so-called computational social
science research, a discipline aimed at applying method-
ologies from the computer sciences to questions asked by
social scientists [15]. While the range of possible applica-
tions of such methodologies to social science questions is
bounded only by the creativity and imagination of the
researcher, here we focus on two types of insights that
have recently attracted a considerable amount of atten-
tion among researchers and practitioners alike: the pre-
diction of (1) relatively stable psychological traits that help
explain consumers’ general tendency to think, feel and
behave in a certain way, and (2) malleable psychological
states that express consumers’ attitudes and emotions in-
the-moment and help to put their behavior in context.
Predicting consumers’ psychological traits
The investigation of stable psychological traits such as
personality, regulatory focus, or need for cognition, has a
long-standing tradition in consumer behavior research
[16]. One of the most consistent findings suggests that
consumers show more positive cognitive, emotional and
behavioral responses to products, brands or marketing
messages that match their own psychological traits [e.
g.,17–20]. For example, an extroverted and open-minded
consumer might experience more positive emotions and
report a higher intention towards a retail brand that
specializes in flashy and unusual clothes, or that uses
extroverted and creative language to advertise their pro-
ducts (e.g., ‘Stand out from the crowd and feel unique with
our latest spring collection’). Businesses have long used
such insights for branding and advertising purposes [e.
g.,21].
However, because unlike demographics and past pur-
chases, latent psychological traits cannot be observed
directly, the opportunities to target consumers and per-
sonalize advertising based on psychological traits have
been limited. If a mobile phone provider, for instance,
decided to create a strong extroverted brand, it was very
difficult to focus its advertising efforts on extroverted
consumers short of choosing media channels (e.g., TV
shows) that are predicted based on questionnaires or
managerial judgement to have a larger proportion of
extroverts. Instead, the branded marketing message
had been primarily focused on mass marketing, broad-
casting to large and heterogeneous audiences, thereby
limiting its effectiveness.
In the age of Big Data, however, psychological traits –
including personality, IQ and political orientation – can
be accurately predicted from consumers’ digital foot-
prints. Researchers have demonstrated the ability to
accurately infer personal traits from (a) personal websites
[22], (b) Facebook or Twitter profiles [23,24

,25], (c)
blogs [26], and (d) language use [27
,28

,29,30]. This
digital form of psychometric assessment promises to be a
game changer in the application and empirical evaluation
of psychographic marketing. In an early pioneering study,
for example, Hauser and colleagues inferred cognitive
styles (e.g., analytic vs. emotional) from clickstream data
and showed that matching a website’s ‘look and feel’ to
consumers’ 
dominant 
motivational 
orientation 
can
increase sales by up to 20% [7]. Similarly, Matz and
colleagues showed that inferring the personality of Face-
book users from their Likes, and matching the content of
real advertising campaigns (products and marketing mes-
sages) to their dominant personality traits can significantly
increase click-through and conversion rates [31

]. As the
digital assessment of psychological traits becomes more
widespread and readily available (e.g., LIWC for comput-
erized text analysis; ApplyMagicSauce and StatSocial for
personality predictions), consumer behavior scholars will
be able to build on this early research and test the
effectiveness of psychographic targeting in different
domains (e.g., retail, charitable giving, political campaign-
ing) and channels (e.g., social media, email, in-store),
using different psychological traits (e.g., personality, cog-
nitive style, motivational orientations), and different
8 
Big data in the behavioural sciences
Current Opinion in Behavioral Sciences 2017, 18:7–12 
www.sciencedirect.com
Case 3:21-cv-01418-EMC     Document 159-5     Filed 02/06/23     Page 3 of 7

outcome measures (e.g. clicks, purchases, long-term
retention).
Turning customer data into meaningful psychological
profiles offers tremendous opportunities for a more holis-
tic Customer Relations Management [CRM; ,32] that
bridges the gap between online and offline channels.
For example, knowing that a consumer follows a cognitive
style that is analytical rather than emotional, makes it
possible for both computers online and salespeople in
brick and mortar stores to adapt their communication to
the preferences of the customer.
Predicting consumers’ psychological states
As we have outlined, psychological traits play an impor-
tant role in understanding and predicting consumer
behavior. However, marketing researchers have long rec-
ognized that they cannot account for the full variation in
consumer behavior [33]. This is, because psychological
traits do not operate in a vacuum, but instead are
expressed in a certain context, these traits are often
influenced by situational factors [34,35]. For example,
consumers who are in a positive mood use more heuristic
– rather than systematic – information processing and
evaluate products and brands more favorably [for an
overview on the effect of mood on consumer behaviour
see Ref. [36]]. Hence marketers can benefit from paying
close attention to and capitalize on customers’ psycho-
logical states.
However, because of the transient nature of psychological
states identifying such states in real time is even more
challenging than identifying psychological traits. Similar
to psychological traits, psychological states have tradition-
ally been tied to questionnaire measures [e.g., the PANAS
scale for positive and negative affect; [37]]. However,
these have been mainly performed for academic purposes
as the ability of firms to measure and act in real time on
varying psychological states using surveys is largely
impractical. Fortunately, new data sources and advances
of analytics techniques make psychological traits predict-
able from a broad variety of digital footprints collected in
real time [see e.g.,38,39
]. Consumers’ mood and emotions
have been successfully predicted from spoken and writ-
ten language [40], video [41], wearable devices [42],
smartphone sensor data [43

], and even information
obtained from the environment such as weather or physi-
cal location [44].
While marketers have long used retrospective analyses of
consumer sentiment in the study of online word-of-
mouth [45,46], the ability to assess consumers’ psycho-
logical states and sentiment in real time provides con-
sumer behavior researchers and practitioners with tre-
mendous opportunities to personalize marketing content
to the immediate psychological needs of consumers.
Context-aware recommendation systems, for example,
can use information on consumers’ mood or emotions
to increase the relevance of the content that is suggested
to the user [47]. Such context-aware recommenders, that
take into account consumers’ emotions, have shown
improved recommendations for music [48], movies
[49,50], and images [51].
Combining psychological traits and states
The combination of psychological traits (variability across
consumers) and psychological states (variability within
consumers over time) offers an unprecedented under-
standing of consumers’ unique needs as they relate to the
situation-specific expressions of more stable motivations
and preferences [33; also compare to the theory of free
traits, 52]. For example, extroverted consumers might be
more likely to respond to personality-matched advertise-
ments [e.g.,19] when they are in an extroverted situation
that highlights and reinforces their extroverted innate
nature or when they find themselves in an introverted
situation that lacks the excitement and stimulation they
need to thrive. The availability of data and analysis tools
to investigate personality traits and states in real time,
provide a fruitful avenue to exploring the interesting
interactions between personality traits and states and
how consumers may react to offer that leverage such
interactions.
Figure 1 summarizes the outlined opportunities of using
Big Data in the context of consumer research. As we have
discussed throughout the paper, the wealth of personal
consumer information available at little to no cost makes
it possible to not only predict consumer outcomes, but to
also understand consumers’ psychological needs and
motivations at both the state and trait levels. Understand-
ing consumers’ psychological states and traits can then be
used to better match the firm’s marketing offerings to
customers’ needs and preferences, and hence improve
business and consumer outcomes.
Opportunities and challenges
The combination of information about ‘what one does’
with deeper understanding of ‘who one is’ offers tremen-
dous opportunities to not only boost the effectiveness of
marketing campaigns but also to help consumers make
better decisions. The pre-selection of content that is in
line with consumers’ psychological needs can alleviate
the problem of choice overload [53,54] and help consu-
mers to maximize the satisfaction and happiness they gain
from their choices [55]. In addition, psychologically-cus-
tomized health messages are known to be effective in
changing behaviors among patients and groups who are at
risk [56,57]. Targeting highly neurotic individuals who
display early signs of depressions with ads that guide
them to self-help pages or offer professional advice, for
example, could have a tremendous positive impact on the
well-being of some of the more vulnerable members of
society, and even save lives.
Using Big Data as a window into consumers’ psychology Matz and Netzer 
9
www.sciencedirect.com 
Current Opinion in Behavioral Sciences 2017, 18:7–12
Case 3:21-cv-01418-EMC     Document 159-5     Filed 02/06/23     Page 4 of 7

Alongside the benefits psychologically-personalized mar-
keting provides, it also raises new ethical challenges.
While psychological targeting can help consumers make
better choices, it could also be used in a way that exploits
‘weaknesses’ in a person’s character. For example, one
could target individuals who are prone to compulsive or
addictive behavior [58] with ads for an online casino, or
exclude them from receiving insurance ads. In fact, Face-
book was recently criticized for analyzing teenagers’
emotional or mental state using their Facebook profiles.
While Facebook said it does not currently use such
inferences for targeting, even the collection of such data
raised consumers’ ethical concerns. This more critical
side of increasingly personalized marketing is reflected
in general public skepticism [59,60]. A 2010 survey of
American Internet users showed that less than 20%
expressed a preference for targeted ad, while 64% viewed
personalized advertising as ‘intrusive’ [59]. In 2012, this
skepticism reached a public peak in response to a
‘scandal’ involving the U.S. retail giant Target. Using
data-driven recommendation algorithms, Target had pro-
moted baby equipment to a pregnant teenage girl in
Minnesota, whose parents had previously been unaware
of the pregnancy. With the introduction of even more
sophisticated prediction algorithms that not only analyze
individual behaviors but make inferences about a con-
sumers’ intimate psychological traits and states, these
concerns are unlikely to change for the better. We
therefore suggest to use the knowledge of consumers’
psychological traits to provide optional services that con-
sumers can actively opt-in to. Given that privacy concerns
are known to negatively impact the effectiveness of
personalized advertising [61], while giving consumers
more control over their personal information positively
affects their willingness to click on personalized ads [62
],
such an approach is not only in the interest of consumers
but eventually in the best self-interest of businesses. By
implementing psychologically-personalized targeting in a
transparent way that gives data ownership and control to
consumers, businesses can avoid the risk of reputational
damage and instead turn psychological customization into
a desirable component of their value proposition to
customers.
Conclusion
Taken together, the ability to predict consumers’ psy-
chological traits and states from their digital footprints
offers exciting new opportunities for digital marketing.
We expect both researchers and practitioners to go
beyond the understanding and prediction of psychologi-
cal states and traits and towards real-time ‘optimization’
of marketing actions on the basis of these predictions.
Much like in the scene in the science fiction movie
Minority Report, where advertising billboards are person-
alized to the emotional state of the person walking past
them, businesses will be able to optimize the advertising a
10 
Big data in the behavioural sciences
Figure 1
Psychological Traits
Psychological States
Digital Records
Consumer Outcomes
•    Big 5 Personality Traits
•    Values
•    Regulatory Focus
•    Cognitive Styles
•    Intelligence
•    Discounting
•    Spendthrift/Tightwad
•    Preferences and Liking
•    Purchase Behavior
•    Post-Purchase Satisfaction
•    Customer Lifetime Value
•    Customer Retention
•    Competitor analysis
•    Brand Perception/
      Awareness
•    Risk Aversion
•    ...
•    Purchase History
•    Browsing History
•    Search Queries
•    Social Media Profiles
     (e.g. Facebook, Twitter)
•    Personal Blogs
•    Wearable Devices (e.g.
     Smartphones, Fitbits)
•    Product Reviews
•    ...
•    ...
•    ...
•    Mood
•    Emotions
•    Alertness
•    Attention
•    Stress
Current Opinion in Behavioral Sciences 
Leveraging Big Data to infer psychological traits and states and affect customer behavior.
Current Opinion in Behavioral Sciences 2017, 18:7–12 
www.sciencedirect.com
Case 3:21-cv-01418-EMC     Document 159-5     Filed 02/06/23     Page 5 of 7

consumer is exposed to in real-time and at a level of detail
never before possible. For example, one could use infor-
mation about a person’s momentary heart rate extracted
through their headphones to determine which song to
play next, extract emotions from a person’s facial expres-
sion to change the color scheme of a website, or recom-
mend the next tourist attraction in a new city as a function
of the person’s predicted personality and their current
level of physical activity. We encourage researchers to
continue to explore these exciting opportunities.
Acknowledgement
Sandra C Matz was funded by the German National Merit Foundation.
References and recommended reading
Papers of particular interest, published within the period of review,
have been highlighted as:

 
of special interest


 of outstanding interest
1.



Wedel M, Kannan PK: Marketing analytics for data-rich
environments. J. Mark. 2016, 80:97-121.
Wedel and Kannan offer a critical review of marketing analytics methods.
Examining different types of data (e.g. structured vs. unstructured, firm
internal vs. external), they review the potential of these methods and
subsequently highlight current and future directions for new analytical
tools with regard to (a) optimized marketing-mix spending, (b) persona-
lization, and (c) data security.
2.



van den Driest F, Sthanunathan S, Weed K: Building an insights
engine. Harvard Bus. Rev. 2016, 94:15.
Van den Driest et al. (2016) provide a practitioner-oriented discussion on
how to successfully implement customer-centricity as a powerful source
of competitive advantage. Focusing on the retail giant Unilever, they
outline operational and people characteristics that facilitate the devel-
opment and application of highly functional “insight engines” on the basis
of Big Data.
3. 
Jacobs BJD, Donkers B, Fok D: Model-based purchase
predictions for large assortments. Mark. Sci. 2016, 35:389-404.
4. 
Ghose A, Ipeirotis PG, Li B: Designing ranking systems for
hotels on travel search engines by mining user-generated and
crowdsourced content. Mark. Sci. 2012, 31:493-520.
5. 
Lu S, Xiao L, Ding M: A video-based automated recommender
(VAR) system for garments. Mark. Sci. 2016, 35:484-510.
6. 
Linden G, Smith B, York J: Amazon.com recommendations:
item-to-item collaborative filtering. IEEE Comput. Soc. 2003,
7:76-80.
7.



Hauser JR, Urban GL, Liberali G, Braun M: Website morphing.
Mark. Sci. 2009, 28:202-223.
Hauser et al. demonstrate the value of dynamic website morphing in a
large-scale experiment using data from 835 BT Group (former British
Telecom) customers. They infer cognitive styles (e.g. analytic vs. emo-
tional) from clickstream data and show that matching a website’s “look
and feel” to consumers’ dominant motivational orientation can increase
sales by up to 20%.
8. 
Trusov M, Ma L, Jamal Z: Crumbs of the cookie: user profiling in
customer-base analysis and behavioral targeting. Mark. Sci.
2016, 35:405-426.
9. 
Culotta A, Cutler J: Mining brand perceptions from twitter
social networks. Mark. Sci. 2016, 35:343-362.
10. Tirunillai S, Tellis GJ: Mining marketing meaning from online
chatter: strategic brand analysis of big data using latent
dirichlet allocation. J. Mark. Res. 2014, 51:463-479.
11. Netzer O, Feldman R, Goldenberg J, Fresko M: Mine your own
business: market-structure surveillance through text mining.
Mark. Sci. 2012, 31:521-543.
12. Davenport TH, Harris JG, Kohli AK: How do they know their
customers so well? MIT Sloan Manage. Rev. 2001, 42:63.
13. Podsakoff PM, Organ DW: Self-reports in organizational
research: problems and prospects. J. Manage. 1986, 12:531-
544.
14. Kosinski M, Matz SC, Gosling SD, Popov V, Stillwell D: Facebook
as a research tool for the social sciences. Am. Psychol. 2015,
70:543-556.
15. Lazer D, Pentland AS, Adamic L, Aral S, Barabasi AL, Brewer D,
Christakis N, Contractor N, Fowler J, Gutmann M: Life in the
network: the coming age of computational social science. Sci.
(New York, NY) 2009, 323:721.
16. Kotler P, Armstrong G: Principles of Marketing. pearson education;
2010.
17. Aaker JL: The malleable self: the role of self expression in
persuasion. J. Mark. Res. 1999, 36:45-57.
18. Sirgy MJ: Using self-congruity and ideal congruity to predict
purchase motivation. J. Bus. Res. 1985, 13:195-206.
19. Hirsh JB, Kang SK, Bodenhausen GV: Personalized persuasion:
tailoring persuasive appeals to recipients’ personality traits.
Psychol. Sci. 2012, 23:578-581.
20. Wheeler SC, Petty RE, Bizer GY: Self-schema matching and
attitude change: situational and dispositional determinants of
message elaboration. J. Consum. Res. 2005, 31:787-797.
21. Aaker JL: Dimensions of brand personality. J. Mark. Res. 1997,
34:347-356.
22. Marcus B, Machilek F, Schu¨ tz A: Personality in cyberspace:
personal Web sites as media for personality expressions and
impressions. J. Pers. Soc. Psychol. 2006, 90:1014-1031.
23. Quercia D, Kosinski M, Stillwell D, Crowcroft J: Our Twitter
profiles, our selves: predicting personality with Twitter. IEEE
International Conference on Social Computing 2011, 18:180-185.
24.



Kosinski M, Stillwell D, Graepel T: Private traits and attributes
are predictable from digital records of human behavior. Proc.
Natl. Acad. Sci. 2013, 110:5802-5805.
Kosinski et al. demonstrate the validity of preference-based personality
assessment via social media. Using data of more than 58 thousand
Facebook users, they show that highly intimate demographic and
socio-psychological characteristics (e.g. political orientation, IQ or per-
sonality) can be accurately predicted from people’s Facebook Likes.
25. Youyou W, Kosinski M, Stillwell D: Computer-based personality
judgments are more accurate than those made by humans.
Proc. Natl. Acad. Sci. U. S. A. 2014, 112:1036-1040.
26. Yarkoni T: Personality in 100,000 words: a large-scale analysis
of personality and word use among bloggers. J. Res. Pers.
2010, 44:363-373.
27.


Netzer O, Lemaire A, Hertzenstien M: When words sweat:
Identifying signals for loan default in the text of loan
applications. Working Paper
Netzer et al. use text-mining and machine-learning tools to automatically
process and analyze the raw text in thousands of loan requests from an
online crowdfunding platform. They find that borrowers, consciously or
not, leave traces of their intentions, circumstances, and personality traits
in the text they write when applying for a loan.
28.



Park G, Schwartz H, Eichstaedt J, Kern ML, Kosinski M, Stillwell D,
Ungar LH, Seligman MEP: Automatic personality assessment
through social media language. J. Pers. Soc. Psychol. 2014,
108:934-952.
Park et al. demonstrate the validity of language-based personality
assessment via social media. Using an open-vocabulary analysis of
the status updates of more than 70 thousand Facebook users, they show
that language-based predictions of personality (a) converge with self and
other reports, (b) accurately discriminate between traits (c) are stable over
time and (d) exhibit correlations with external criteria (e.g. life satisfaction)
similar to those found for self-reports.
29. Schwartz HA, Eichstaedt JC, Kern ML, Dziurzynski L,
Ramones SM, Agrawal M, Shah A, Kosinski M, Stillwell D,
Seligman MEP et al.: Personality, gender, and age in the
Using Big Data as a window into consumers’ psychology Matz and Netzer 
11
www.sciencedirect.com 
Current Opinion in Behavioral Sciences 2017, 18:7–12
Case 3:21-cv-01418-EMC     Document 159-5     Filed 02/06/23     Page 6 of 7

language of social media: the open-vocabulary approach.
PLoS One 2013, 8:e73791.
30. Pennebaker JW, King LA: Linguistic styles: language use as an
individual difference. J. Pers. Soc. Psychol. 1999, 77:1296.
31.



Matz S, Kosinski M, Nave G, Stillwell D: Personality-matching
increases the effectiveness of digital advertising. Working
Paper
Matz et al. demonstrate the effectiveness of personality-based targeting
in several large-scale experiments on Facebook. They show that inferring
the personality of Facebook users from their Likes, and matching the
content of real advertising campaigns (products and marketing mes-
sages) to their dominant personality traits can significantly increase click-
through and conversion rates.
32. Odekerken-Schro¨ der G, De Wulf K, Schumacher P:
Strengthening outcomes of retailer–consumer relationships:
the dual impact of relationship marketing tactics and
consumer personality. J. Bus. Res. 2003, 56:177-190.
33. Belk RW: Situational variables and consumer behavior. J.
Consum. Res. 1975, 2:157-164.
34. Kenrick DT, Funder DC: Profiting from controversy: lessons
from the person-situation debate. Am. Psychol. 1988, 43:23.
35. Fleeson W, Noftle E: The end of the person–situation debate: an
emerging synthesis in the answer to the consistency question.
Soc. Pers. Psychol. Compass 2008, 2:1667-1684.
36. Bagozzi RP, Gopinath M, Nyer PU: The role of emotions in
marketing. J. Acad. Mark. Sci. 1999, 27:184-206.
37. Watson D, Clark La, Tellegen a: Development and validation of
brief measures of positive and negative affect: the PANAS
scales. J. Pers. Soc. Psychol. 1988, 54:1063-1070.
38. Zeng Z, Pantic M, Roisman GI, Huang TS: A survey of affect
recognition methods: audio, visual, and spontaneous
expressions. IEEE Trans. Pattern Anal. Mach. Intell. 2009, 31:39-
58.
39.


D’mello SK, Kory J: A review and meta-analysis of multimodal
affect detection systems. ACM Comput. Surv. 2015, 47:43.
D’mello and Kory provide a systematic review of multimodal affect
detection systems. Based on a quantitative review and meta-analysis
of 90 peer-reviewed affect detection systems, they show that (a) the
majority of systems relies on person-dependent models, fusing audio and
visual, (b) multimodal systems were consistently better than unimodal
systems, and (c) systems were substantially less accurate for natural than
for acted emotional reactions.
40. Cowie R, Douglas-Cowie E, Savvidou* S, McMahon E, Sawey M,
Schro¨ der M: FEELTRACE: An instrument for recording
perceived emotion in real time. ISCA Tutorial and Research
Workshop (ITRW) on Speech and Emotion 2000.
41. Teixeira T, Wedel M, Pieters R: Emotion-induced engagement in
internet video advertisements. J. Mark. Res. 2012, 49:144-159.
42. AlHanai T, Ghassemi MM: Predicting latent narrative mood
using audio and physiologic data. AAAI 2017.
43.



LiKamWa R, Liu Y, Lane ND, Zhong L: Moodscope: building a
mood sensor from smartphone usage patterns. Proceeding of
the 11th annual international conference on Mobile systems,
applications, and services; ACM: 2013:389-402.
LiKamWa et al. demonstrate the validity of assessing people’s mood on
the basis of their smartphone sensor data. Using smartphone logged data
of 32 participants collected over a period of two months, they show that
people’s daily mood can be accurately predicted from their communica-
tion history and patterns of application usage.
44. Park H-S, Yoo J-O, Cho S-B: A Context-aware Music
Recommendation System Using Fuzzy Bayesian Networks with
Utility Theory: In International Conference on Fuzzy Systems and
Knowledge Discovery. Springer; 2006:970-979.
45. Das SR, Chen MY: Yahoo! for Amazon: sentiment extraction
from small talk on the web. Manage. Sci. 2007, 53:1375-1388.
46. Jansen BJ, Zhang M, Sobel K, Chowdury A: Twitter power:
tweets as electronic word of mouth. J. Am. Soc. Inf. Sci.
Technol. 2009, 60:2169-2188.
47. Zheng Y, Mobasher B, Burke R: Emotions in Context-aware
Recommender Systems: In Emotions and Personality in
Personalized Services. Springer; 2016:311-326.
48. Lee JS, Lee JC: Music for my mood: a music recommendation
system based on context reasoning. European Conference on
Smart Sensing and Context. Springer; 2006:190-203.
49. Winoto P, Tang TY: The role of user mood in movie
recommendations. Expert Syst. Appl. 2010, 37:6086-6092.
50. Shi Y, Larson M, Hanjalic A: Mining mood-specific movie
similarity with matrix factorization for context-aware
recommendation. In Proceedings of the Workshop on Context-
aware Movie Recommendation; ACM: 2010:34-40.
51. Tkal9ci9c M, Burnik U, Koir A: Using affective parameters in a
content-based recommender system for images. User Model.
User-adapt. Interact. 2010, 20:279-311.
52. Little BR: Free traits, personal projects and idio-tapes: three
tiers for personality psychology. Psychol. Inq. 1996, 7:340-344.
53. Iyengar SS, Lepper MR: When choice is demotivating: can one
desire too much of a good thing? J. Pers. Soc. Psychol. 2000,
79:995-1006.
54. Schwartz B, Ward A: Doing better but feeling worse: the
paradox of choice. In Positive Psychology in Practice. Edited by
Linley AP, Joseph S. John Wiley & Sons, Inc.; 2004:86-104.
55. Matz S, Gladstone J, Stillwell D: Money buys happiness when
spending fits our personality. Psychol. Sci. 2016, 27:715-725.
56. Noar SM, Benac CN, Harris MS: Does tailoring matter? Meta-
analytic review of tailored print health behavior change
interventions. Psychol. Bull. 2007, 133:673-693.
57. Mann T, Sherman D, Updegraff J: Dispositional motivations and
message framing: a test of the congruency hypothesis in
college students. Heal. Psychol. 2004, 23:330.
58. Bagby RM, Vachon DD, Bulmash EL, Toneatto T, Quilty LC,
Costa PT: Pathological gambling and the five-factor model of
personality. Pers. Individ. Dif. 2007, 43:873-880.
59. McDonald AM, Cranor LF: Americans’ attitudes about internet
behavioral advertising practices. In Proceedings of the 9th
Annual ACM Workshop on Privacy in the Electronic Society; ACM:
2010:63-72.
60. Ur B, Leon PG, Cranor LF, Shay R, Wang Y: Smart, useful, scary,
creepy: perceptions of online behavioral advertising. In
Proceedings of the Eighth Symposium on Usable Privacy and
Security; ACM: 2012:4.
61. Goldfarb A, Tucker CE: Privacy regulation and online
advertising. Manage. Sci. 2011, 57:57-71.
62.


Tucker CE: Social networks, personalized advertising, and
privacy controls. J. Mark. Res. 2014, 51:546-562.
Tucker investigates how consumers’ perceived control over privacy
affects their willingness to engage with personalized advertising. Using
data from a randomized field experiment, she demonstrates that giving
people more control over their personally identifiable information
increases– rather than decreases – the likelihood of them clicking on
personalized ads.
12 
Big data in the behavioural sciences
Current Opinion in Behavioral Sciences 2017, 18:7–12 
www.sciencedirect.com
Case 3:21-cv-01418-EMC     Document 159-5     Filed 02/06/23     Page 7 of 7

File and source

File

gov.uscourts.cand.374304.159.5.pdf

Size

325,040 bytes

SHA-256

e1030d28be76e9f56e7bd9b313d5c452a3f3bae9603147987f50d339da9116c6

Our copy

gov.uscourts.cand.374304.159.5.pdf

Original

PACER (login required)