Decision Making and Recommender Systems Marko Tkal i Johannes - - PowerPoint PPT Presentation

Personality and Emotions in Decision Making and Recommender Systems

Marko Tkalčič

Johannes Kepler University, Austria

Giovanni Semeraro

University of Bari Aldo Moro, Italy

Marco de Gemmis

University of Bari Aldo Moro, Italy

Bozen-Bolzano, September 18, 2014

Semantic Web Access and Personalization research group

http://www.di.uniba.it/~swap

Outline

 Background  The role of Personality in Decision Making and Recommender Systems

 Models  Acquisition  Personality and Decision Making  Personality in RecSys – examples

 The role of Emotions in Decision Making and Recommender Systems

 Models  Acquisition  Emotions and Decision Making  Emotions in RecSys – examples

 Focus: Emotions as Implicit Feedback for evaluation purposes  Conclusions and take away notes

2

Outline

 Background  The role of Personality in Decision Making and Recommender Systems

 Models  Acquisition  Personality and Decision Making  Personality in RecSys – examples

 The role of Emotions in Decision Making and Recommender Systems

 Models  Acquisition  Emotions and Decision Making  Emotions in RecSys – examples

 Focus: Emotions as Implicit Feedback for evaluation purposes  Conclusions and take away notes

3

Background – The Big Picture

The Big Picture -1

5

Decision Making Recommender Systems

The Big Picture - 2

6

Decision Making Recommender Systems Personality Emotions

The Big Picture - 3

7

Decision Making Recommender Systems Personality Emotions Models Models Acquisition Acquisition

The Big Picture - 4

8

Decision Making Recommender Systems Personality Emotions Models Models Acquisition Acquisition Examples Datasets Publishing

• pportunities

Temporal aspects

 Personality = enduring personal characteristics

(Excerpt of a) user‘s lifetime personality

Temporal aspects

(Excerpt of a) user‘s lifetime personality mood

 Personality = enduring personal characteristics  Mood = slow changes (positive/negative)

Temporal aspects

(Excerpt of a) user‘s lifetime personality mood emotions

 Personality = enduring personal characteristics  Mood = slow changes (positive/negative)  Emotion = triggered, fast changes, more specific, more intense

Outline

 Background  The role of Personality in Decision Making and Recommender Systems

 Models  Acquisition  Personality and Decision Making  Personality in RecSys – examples

 The role of Emotions in Decision Making and Recommender Systems

 Models  Acquisition  Emotions and Decision Making  Emotions in RecSys – examples

 Focus: Emotions as Implicit Feedback for evaluation purposes  Conclusions and take away notes

12

Personality in Decision Making and Recommender Systems

What is personality?

 Personality: accounts for individual differences ( = explains the variance in users)

Cain, S. (2013). Quiet: The Power of Introverts in a World That Can’t Stop Talking. Broadway Books.

Models of personality – 4 temperaments

 Hippocratess (cca 400 BC)

 Four temperaments

– sanguine (pleasure-seeking and sociable) – choleric (ambitious and leader-like) – melancholic (analytical and quiet) – phlegmatic (relaxed and peaceful)

Models of personality - FFM

 The five factor model (FFM) – Big5:

 Extraversion  Agreeableness  Conscientousness  Neuroticism  Openness

(McCraMcCrae, R. R., & John, O. P. (1992). An Introduction to the Five-Factor Model and its Applications. Journal of Personality, 60(2), p175 – 215.

Models of personality - others

 RIASEC occupational model:



Realistic (Doers),



Investigative (Thinkers),



Artistic (Creators),



Social (Helpers),



Enterprising (Persuaders)



Conventional (Organizers)

 Bartle gamers model:



Killers: interfere with the functioning of the game world or the play experience of other players



Achievers: accumulate status tokens by beating the rules-based challenges of the game world



Explorers: discover the systems governing the

• peration of the game world



Socializers: form relationships with other players by telling stories within the game world

 Myers-Briggs Personality Type



Extraversion (E) or Introversion (I).



Sensing (S) or Intuition (N).



Thinking (T) or Feeling (F).



Judging (J) or Perceiving (P).

 Learning styles (Felder and Silverman Learning Style Model):



active/reflective,



sensing/intuitive,



visual/verbal,



sequential/global

 Thomas-Kilmann Conflict Mode Instrument



Assertiveness



Cooperativeness

 CORRELATIONS

J.L Holland: Making vocational choices, Prentice-Hall, Englewood Cliffs (1973) http://www.gamasutra.com/view/feature/134842/personality_and_play_styles_a_.php El-Bishouty, M. M., Chang, T.-W., Graf, S., & Chen, N.-S. (2014). Smart e-course recommender based on learning styles. Journal of Computers in Education, 1(1), 99–111. doi:10.1007/s40692-014-0003-0 Furnham, A. (1996). The big five versus the big four: the relationship between the Myers-Briggs Type Indicator (MBTI) and NEO-PI five factor model of personality. Personality and Individual Differences, 21(2), 303–307. doi:10.1016/0191-8869(96)00033-5

• J.L Holland
• Making vocational choicesPrentice-Hall, Englewood Cliffs (1973)
• J.L Holland
• Making vocational choicesPrentice-Hall, Englewood Cliffs (1973)

Explicit acquisition of personality

 Questionnaires: IPIP; TIPI … (from 10 to severral 100s questions)  TIPI:

 I see myself as (1-5):

–

• 1. _____ Extraverted, enthusiastic.

–

• 2. _____ Critical, quarrelsome.

–

• 3. _____ Dependable, self-disciplined.

–

• 4. _____ Anxious, easily upset.

–

• 5. _____ Open to new experiences, complex.

–

• 6. _____ Reserved, quiet.

–

• 7. _____ Sympathetic, warm.

–

• 8. _____ Disorganized, careless.

–

• 9. _____ Calm, emotionally stable.

–

• 10. _____ Conventional, uncreative.

http://homepage.psy.utexas.edu/HomePage/Faculty/Gosling/tipi%20site/tipi.htm Gosling, S. D., Rentfrow, P. J., & Swann, W. B. (2003). A very brief measure of the Big-Five personality domains. Journal of Research in Personality, 37(6), 504–528. doi:10.1016/S0092-6566(03)00046-1

Implicit acquisition of personality

 Social media:

 Facebook (Kosinski et al., 2013)  Twitter (Golbeck et al., 2011, Quercia et al., 2011)  Emails (Shen et al., 2013)  Blogs (Nowson et al., 2007)

Kosinski, M., Stillwell, D., & Graepel, T. (2013). Private traits and attributes are predictable from digital records

• f human behavior. Proceedings of the National Academy of Sciences, 2–5. doi:10.1073/pnas.1218772110

Golbeck, J., Robles, C., & Turner, K. (2011). Predicting personality with social media. Proceedings of the 2011 Annual Conference Extended Abstracts on Human Factors in Computing Systems - CHI EA ’11, 253. doi:10.1145/1979742.1979614 Quercia, D., Kosinski, M., Stillwell, D., & Crowcroft, J. (2011). Our Twitter Profiles, Our Selves: Predicting Personality with Twitter. In 2011 IEEE Third Int’l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing (pp. 180–185). IEEE. doi:10.1109/PASSAT/SocialCom.2011.26 Shen, J., Brdiczka, O., & Liu, J. (2013). Understanding Email Writers: Personality Prediction from Email

• Messages. User Modeling, Adaptation, and Personalization, 318–330. doi:10.1007/978-3-642-38844-6_29

Nowson, S., & Oberlander, J. (2007). Identifying more bloggers: Towards large scale personality classification

• f personal weblogs. International Conference on Weblogs and Social Media. Retrieved from

http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.64.2021

Implicit acquisition of personality

 From social media (e.g. facebook, twitter)  Features:



Latent factors



Social network features (followers ..)

Kosinski, M., Stillwell, D., & Graepel, T. (2013). Private traits and attributes are predictable from digital records of human behavior. Proceedings of the National Academy of Sciences, 2–5. doi:10.1073/pnas.1218772110

Kosinski et al., 2013 results

 Correlation  Test/retest correlation (questionnaire accuracy) - transparent Kosinski, M., Stillwell, D., & Graepel, T. (2013). Private traits and attributes are predictable from digital records of human behavior. Proceedings of the National Academy of Sciences, 2–5. doi:10.1073/pnas.1218772110

How it fits into decision making?

 Personality is related to decision making styles:

 Myers-Briggs T/F: objective principles and impersonal facts

(Thinking) or do you put more weight on personal concerns and the people involved (Feeling)?

 Coping with Decisional Conflict (vigilance, buck-passing,

procrastination and hypervigilance) (Deniz, 2011)

 Career decision-making (Pecjak, 2007)

Pečjak, S., & Košir, K. (2007). Personality, motivational factors and difficulties in career decision-making in secondary school students. Psihologijske Teme, 16, 141–158. Deniz, M. (2011). An Investigation of Decision Making Styles and the Five-Factor Personality Traits with Respect to Attachment Styles. Educational Sciences: Theory and Practice, 11(1), 105–114. Mann, L., Burnett, P., Radford, M., & Ford, S. (1997). The Melbourne Decision Making Questionnaire: An instrument for measuring patterns for coping with decisional conflict. Journal of Behavioral Decision Making, 10(1), 1–19. McCrae, R. R., & Costa, P. T. (1989). Reinterpreting the Myers-Briggs Type Indicator from the perspective of the five- factor model of personality. Journal of Personality, 57(1), 17–40. doi:10.1111/1467-6494.ep8972588

Personality in Recommender Systems

 New user problem  Diversity  Preferences (genres)  Group recommenders  Browsing Styles  Mood regulation

A personality-based user similarity measure

 Collaborative filtering recommender (CFR) systems:



Similar users have similar preferences



Rating-based similarity measures -> Personality based similarity measure

Which content should I watch tonight?

Tkalcic, M., Kunaver, M., Košir, A., & Tasic, J. (2011). Addressing the new user problem with a personality based user similarity measure. DEMRA 2011, UMMS 2011 Elahi, M., Braunhofer, M., Ricci, F., & Tkalcic, M. (2013). Personality-based active learning for collaborative filtering recommender systems. AI*IA 2013: Advances in Artificial Intelligence, 360–371. doi:10.1007/978-3- 319-03524-6_31

Using personality to diversify recommendations

FIT FIT FIT DIVERSE DIVERSE DIVERSE Are you satisfied with the recommendations?

Wu, W., Chen, L., & He, L. (2013). Using personality to adjust diversity in recommender systems. Proceedings of the 24th ACM Conference on Hypertext and Social Media - HT ’13, (May), 225–229. doi:10.1145/2481492.2481521

Using personality to diversify recommendations

Openness to new experiences

FIT DIVER SE FIT DIVER SE DIVER SE FIT FIT FIT DIVER SE DIVER SE FIT FIT DIVER SE

high low

Are you satisfied with the recommendations? Are you satisfied with the recommendations?

FIT FIT DIVER SE DIVER SE DIVER SE

Are you satisfied with the recommendations?

Wu, W., Chen, L., & He, L. (2013). Using personality to adjust diversity in recommender systems. Proceedings of the 24th ACM Conference on Hypertext and Social Media - HT ’13, (May), 225–229. doi:10.1145/2481492.2481521

Personality is correlated with Music Preferences

 Intense/rebellious  Openness  Upbeat/Conventional Extraversion, Agreeableness,Conscientiousness  Energetic/Rhytmic Extraversion, Agreeableness

Rentfrow, P. J., & Gosling, S. D. (2003). The do re mi’s of everyday life: The structure and personality correlates

• f music preferences. Journal of Personality and Social Psychology, 84(6), 1236–1256. doi:10.1037/0022-

3514.84.6.1236

Personality and group RS

 (Garcia et al, 2009)

 Group personality composition  TKI Conflict personality modes (assertiveness, cooperativeness)  MovieLens+70 students  „group goes to the cinema“

 (Kompan et al, 2014)

 TKI, NEO-FFI  Small scale (9 users) groups of 3  Movie recommendations

Recio-Garcia, J. A., Jimenez-Diaz, G., Sanchez-Ruiz, A. A., & Diaz-Agudo, B. (2009). Personality aware recommendations to groups. In Proceedings of the third ACM conference on Recommender systems - RecSys ’09 (p. 325). New York, New York, USA: ACM Press. doi:10.1145/1639714.1639779 Quijano-Sanchez, L., Recio-Garcia, J. a., & Diaz-Agudo, B. (2010). Personality and Social Trust in Group

• Recommendations. 2010 22nd IEEE International Conference on Tools with Artificial Intelligence, (c), 121–126.

doi:10.1109/ICTAI.2010.92 Kompan, M., & Bieliková, M. (2014). Social Structure and Personality Enhanced Group Recommendation. EMPIRE 2014: Emotions and Personality in Personalized Services.

Mood regulation

 Uses and gratification theory: music is used for mood regulation  high on openness, extraversion, and agreeableness more inclined to listen to happy music when they are feeling sad.  high on neuroticism listen to more sad songs when feeling disgusted (neurotic people choose to increase their level of worry)

Ferwerda, Schedl, Tkalčič (2014), Personality & Emotional States: Understanding User’s Music Listening Needs to Enhance Recommender Systems, submitted to CHI 2015

Music Browsing Style

Ferwerda, Yang, Schedl, Tkalčič (2014), Personality Traits Predict Music Category Preferences, submitted to CHI 2015

Outline

 Background  The role of Personality in Decision Making and Recommender Systems

 Models  Acquisition  Personality and Decision Making  Personality in RecSys – examples

 The role of Emotions in Decision Making and Recommender Systems

 Models  Acquisition  Emotions and Decision Making  Emotions in RecSys – examples

 Focus: Emotions as Implicit Feedback for evaluation purposes  Conclusions and take away notes

31

Emotions in Decision Making and Recommender Systems

Overview of emotions

 Emotions are complex human experiences  Evolutionary based  Several definitions  We take simple models, easy to incorporate in computers:

 Basic emotions  Dimensional model  Circumplex model

Basic emotions

 Discrete classes model  Different sets  Darwin: Expression of emotions in man and animal  Ekman definition (6 + neutral):

 Happiness  Anger  Fear  Sadness  Disgust  Surprise

Dimensional model

 Three dimensions

 Valence  Arousal  Dominance

 Each emotive state is a point in the VAD space

Circumplex model

 Maps basic emotions dimensional model

Arousal Valence

high negative positive low

neutr al sadne ss fear disgu st surpri se joy anger

How to detect emotions?

 Explicit vs. Implicit  Explicit

 Questionnaires (SAM)

 Implicit:

 Work done in the affective computing

community

 Different modalities (sources):

– Facial actions (video) – Physiological signals ( GSR, EEG) – Voice – Posture – ...

 ML techniques

– Classification (basic emotions) – Regression (dimensional model)

Emotion detection from videos of facial expressions

 Problem statement:

 Explicit affective labeling has drawbacks:

– Annoying – Time consuming – Potentially inaccurate in real applications

 Proposed solution:

 Implicit affective labeling through emotion detection

from facial video

 Aggregation of emotions detected from several users

Experiment

 2 datasets:



Posed (Kanade Cohn)



Spontaneous (LDOS-PerAff-1)

 Input: Video streams of facial expressions as responses to visual stimuli  Output: emotive states as distinct classes

Gabor features kNN Emotive state

Results and conclusions

 Posed dataset: accuracy = 92 %  Spontaneous dataset: accuracy = 62%  Reasons for bad results:

 Weak learning supervision  Non optimal video acquisition (face rotation, occlusions,

changing lightning ...)

 Non extreme facial expressions

Tkalčič, M., Odić, A., & Košir, A. (2013). The impact of weak ground truth and facial expressiveness on affect detection accuracy from time-continuous videos of facial expressions. Information Sciences, 249, 13–23. doi:10.1016/j.ins.2013.06.006 Tkalcic, M., Odic, A., Kosir, A., & Tasic, J. (2013). Affective Labeling in a Content-Based Recommender System for Images. IEEE Transactions on Multimedia, 15(2), 391–400. doi:10.1109/TMM.2012.2229970

Emotion detection in social media

 Microblogs: 1 tweet ->{happy/unhappy, active/inactive}  Features:



Unigrams



Emoticons



Punctuation features



Negation features

Hasan, M., Rundensteiner, E., & Agu, E. (n.d.). EMOTEX : Detecting Emotions in Twitter Messages., SocialCom2014

The problem researchers face

DM = rational + emotional

 The chooser came under the influence of emotions

 Affective mechanisms that work on an unconscious

automatic level

 Immediate emotions

OR  She intentionally consults her feelings about options, and uses that information to guide the decision process

 Information value of emotions

43

The affect heuristic

 A mental shortcut

 Quick decision based on current emotions and feelings  No need to complete an extensive search for information

 Equivalent of "going with your gut instinct"

44

Slovic, P., Finucane, M., Peters, E., & MacGregor, D. G. (2002). The affect heuristic. In T. Gilovich, D. Griffin, & D. Kahneman (Eds.), Heuristics and biases: The psychology of intuitive

• judgment. Cambridge: Cambridge University, Press.

Some affect heuristics

 Risks and Benefits of options evaluated depending on the positive or negative feelings associated with a stimulus  What about buying a fast luxury car?

45

Fear Appeals

46

Did your perception of the risks of buying a fast car change?

Somatic marker hypothesis

 Cognitive overload of complex and conflicting choices

 somatic markers and their evoked emotions can help

decide

 Physiological signals are consciously or unconsciously associated with their past outcomes

 Somatic markers associated with positive / negative

• utcomes  tendency to choose / avoid options

 Experience-based

47

Damasio, A.R. (1996) "The Somatic Marker Hypothesis and the Possible Functions of the Prefrontal Cortex". Philosophical Transactions 351 (1346): 1413–1420, Damasio, A.R. (1994) Descartes' Error: Emotion, Reason, and the Human Brain, Putnam, 1994.

Emotions as Contexts in Context-aware Recommender Systems (I)

48

 Emotions useful as contextual conditions for context- aware-splitting [Zheng2013]

 Emotion-linked context makes an important contribution

when added to other dimensions (e.g. Time)

 Emotions incorporated into contextual modeling process to assist user-based CF [Zheng2013]

 Allows to define the role of emotions with respect to the

specific components of the recommendation process

 Mood and dominant emotion are influencial for computing

user similarity and selecting neighbors

 Emotional tags associated with points of interest for location-based music recommendation [Kaminskas 2011]

[Zheng2013] Yong Zheng, Bamshad Mobasher, Robin D. Burke: The Role of Emotions in Context-aware Recommendation. Decisions@RecSys 2013: 21-28 [Kaminskas2011] Marius Kaminskas and Francesco Ricci. 2011. Location-adapted music recommendation using tags. Proceedings of UMAP '11, Springer-Verlag, Berlin, Heidelberg, 183-194.

Example of affective user modeling

 We propose to use AFFECTIVE METADATA  Multimedia content ELICITS (induces) emotions  Underlying assumption: users differ in their preferences for emotions

Example of affective user modeling

EMOTION INDUCTION

IAPS Image Stimuli Consumed Item Metadata (Item Profile) Explicit Rating Machine Learning Ground Truth Ratings Predicte d Ratings Confusi

• n

Matrix User Profile generic metadata affective metadata

Tkalčič, M., Burnik, U., & Košir, A. (2010). Using affective parameters in a content-based recommender system for images. User Modeling and User-Adapted Interaction, 20(4), 279–311. doi:10.1007/s11257-010- 9079-z

Social Signal – Hesitation as Affective Feedback

Vodlan, T., Tkalčič, M., & Košir, A. (2014). The impact of hesitation, a social signal, on a user’s quality of experience in multimedia content retrieval. Multimedia Tools and Applications. doi:10.1007/s11042-014- 1933-2

ePoznan.pl- polish startup recsys company

Datasets

 LDOS PerAff-1(images, small scale, emotions, personality)  LDOS CoMoDa (movies, emotions, personality)  myPersonality (facebook activity, personality)

Tkalčič, M., Košir, A., & Tasič, J. (2013). The LDOS-PerAff-1 corpus of facial-expression video clips with affective, personality and user-interaction metadata. Journal on Multimodal User Interfaces, 7(1-2), 143–155. doi:10.1007/s12193-012-0107-7 Košir, A., Odić, A., Kunaver, M., Tkalčič, M., & Tasič, J. F. (2011). Database for contextual personalization. Elektrotehniški Vestnik, 78(5), 270–274. Bachrach, Y., Kosinski, M., Graepel, T., Kohli, P., & Stillwell, D. (2012). Personality and patterns of Facebook

• usage. In Proceedings of the 3rd Annual ACM Web Science Conference on - WebSci ’12 (pp. 24–32). New York,

New York, USA: ACM Press. doi:10.1145/2380718.2380722

Outline

 Background  The role of Personality in Decision Making and Recommender Systems

 Models  Acquisition  Personality and Decision Making  Personality in RecSys – examples

 The role of Emotions in Decision Making and Recommender Systems

 Models  Acquisition  Emotions and Decision Making  Emotions in RecSys – examples

 Focus: Emotions as Implicit Feedback for evaluation purposes  Conclusions and take away notes

54

Focus: Emotions as implicit feedback for assessing serendipity of recommendations

Collaborators/Contributors

56

Marco de Gemmis Pasquale Lops

Semantic Web Access and Personalization research group

http://www.di.uniba.it/~swap

Outline

 Serendipity and Evaluation  Research questions  Operationally induced serendipity:

 Knowledge Infusion (KI) process  Item-to-Item correlation matrix  Random Walk with Restart boosted by KI

 Experimental evaluation

 Noldus FaceReader ™  Dataset  Design of the experiment  Metrics  Questionnaire analysis  Analysis of user emotions

 Conclusions

Serendipity

58

Serendipity in Information Seeking

 Information seeking metaphor investigated in literature (Toms 2000)  Toms suggests 4 strategies

 Blind luck or “role of chance”  random  Pasteur Principle or “chance favors only the prepared mind” 

flashes of insight don’t just happen, but they are the products

• f a “prepared mind”

 Anomalies and exceptions or “searching for dissimilarities” 

identification of items dissimilar to those the user liked in the past

 Reasoning by analogy  abstraction mechanism allowing the

system to discover the applicability of an existing schema to a new situation

(Toms 2000) E. Toms. Serendipitous Information Retrieval. Proceedings of the First DELOS Network of Excellence Workshop on Information Seeking, Searching and Querying in Digital Libraries, Zurich, Switzerland: European Research Consortium for Informatics and Mathematics, 2000. 59

Serendipitous recommendations

 “Suggestions which help the user to find surprisingly interesting items she might not have discovered by herself” (Herlocker et al. 2004)

 Both attractive and unexpected

 “The experience of receiving an unexpected and fortuitous item recommendation” (McNee et al. 2006)  A response to the

• verspecialization

problem and the filter bubble (Pariser 2011)

 tendency to provide the user with items within her existing

range of interests

 suggesting

“STAR TREK” to a science-fiction fan: Accurate but obvious, thus actually not useful

 users don’t want algorithms that produce better ratings, but

sensible recommendations

(Herlocker et al. 2004) Herlocker, L., Konstan, J.A., Terveen, L.G., Riedl, J.T.: Evaluating Collaborative Filtering Recommender Systems. ACM Transactions on Information Systems 22(1): 5–53, 2004. (McNee et al. 2006) S. M. McNee, J. Riedl, and J. A. Konstan. Being accurate is not enough: How accuracy metrics have hurt recommender

• systems. In CHI ’06 Extended Abstracts on Human Factors in Computing Systems, CHI EA ’06, 1097–1101, ACM, New York, NY, USA, 2006.

(Pariser 2011) E. Pariser. The Filter Bubble: What the Internet Is Hiding from You. Penguin Group, May 2011.

60

Evaluation of Serendipity: research questions

 Is the emotional response of the user useful for assessing serendipity?  Can the emotions observed in facial expressions be considered as a trustworthy implicit feedback for assessing the pleasant surprise that serendipity should convey?

61

Operationally induced Serendipity: A Quick Look at the Recommendation Algorithm

 Novel method for computing item similarity

 tries to find “hidden associations” instead of

computing attribute similarity

 knowledge intensive process that allows

deeper understanding of item descriptions

 Knowledge Infusion (KI)

 provides the RecSys with a background

knowledge made from external sources

 Content-based approach that exploits

the knowledge base to compute a correlation index between items

62

Operationally induced Serendipity: Knowledge Infusion (KI)

 Which “words”?

 Words that induce positive emotions  Relevant/attractive words able to surprise

the conversation partner

63

“Language is the Skin of my Thought”

Arundhati Roy. Power Politics. South End Press, January 2001.

“Words” Recommender System

Recommending Words: the Architecture of the KI process

sci-fi conflicts/ fights

KI@Work

CLUE#1

Knowledge Source #1 Knowledge Source #2 Knowledge Source #3

. . .

Knowledge Source #n

CLUE#2 BACKGROUND KNOWLEDGE CLUE#3 CLUE#4 CLUE#5 SPREADING ACTIVATION NETWORK

KEYWORD1 KEYWORD2

…

NEW KEYWORDS ASSOCIATED WITH CLUES

65

• G. Semeraro, M. de Gemmis, P. Lops, P. Basile. An Artificial Player for a Language Game. IEEE Intelligent Systems

27(5): 36-43, 2012.

• P. Basile, M. de Gemmis, P. Lops, G. Semeraro. Solving a Complex Language Game by using Knowledge-based Word

Associations Discovery. IEEE Transactions on Computational Intelligence and AI in Games, 2014 (in press).

66

KI as a novel method for computing associations between items

BM25 retrieval score clues

67

KI as a Serendipity Engine: Item-to-Item similarity matrix  Item-to-Item correlation matrix

wij computed in different ways

 #users co-rated Ii and Ij  cosine similarity between item descriptions  Knowledge Infusion

• Correlation index

Recommendation list computed by Random Walk with Restart (Lovasz 1996) augmented with KI (RWR-KI)

(Lovasz 1996) L. Lovasz. Random Walks on Graphs: a Survey. Combinatronics 2:1–46, 1996.

wij

Evaluation of Serendipity: research questions

 Is the emotional response of the user useful for assessing serendipity?  Can the emotions observed in facial expressions be considered as a trustworthy implicit feedback for assessing the pleasant surprise that serendipity should convey?

68

Experimental Evaluation: Goal

69

 Validation of the hypothesis that recommendations produced by RWR-KI are serendipitous (relevant/attractive & unexpected/surprising)  Not only an issue of metrics!

 Difficulty

• f

detecting and providing an

• bjective

assessment of the emotional response conveyed by serendipitous recommendations

 Difficulty

• f

assessing the user perception

• f

serendipity of recommendations and their acceptance (in terms of relevance and unexpectedness)

 Difficulty of assessing unexpectedness

• M. de Gemmis, P. Lops, G. Semeraro. An Investigation on the Serendipity Problem in Recommender
• Systems. submitted manuscript, 2014.

Experimental Evaluation

70

 2 experiments

 In-vitro  User study

 In-vitro experiment

 Unexpectedness

measured as deviation from a standard prediction criterion (Murakami et al. 2008)

 Standard

prediction criterion: (non-personalized) popularity

 User study

 Analysis performed using Noldus FaceReader™  Allows to analyze users’ facial expressions and gather

implicit feedback about their reactions

(Murakami et

• al. 2008) T.

Murakami, K. Mori, R. Orihara, Metrics for Evaluating the Serendipity of Recommendation Lists, in K. Satoh, A. Inokuchi, K. Nagao, T. Kawamura (Eds.), New Frontiers in Artificial Intelligence, Lecture Notes in Computer Science 4914, pp. 40–46, Springer, 2008.

71

Noldus FaceReader™

 Recognize 6 categories of emotions, proposed by Ekman (1999)

 happiness  anger  sadness

 Classification accuracy

 ~ 90% on Radboud Faces Database (RaFD) (Langner et

• al. 2010)

(Ekman 1999) P. Ekman, Basic Emotions, in T. Dalgleish, M.J. Power (Eds.), Handbook of Cognition and Emotion, 45–60, John Wiley & Sons, 1999. (Langner et al. 2010) O. Langner, R. Doetsch, G. Bijlstra, D.H.J. Wigboldus, S.T. Hawk, A. van Knippenberg. Presentation and Validation of the Radboud Faces Database, Cognition and Emotion 24(8), 1377-1388, 2010.

 fear  disgust  surprise

Experimental Evaluation: Noldus FaceReader™

72

Experimental Evaluation (user study): Dataset

73

 Experimental units: 40 master students (engineering, architecture, economy, computer science and humanities)

 26 male (65%), 14 female (35%)  Age distribution: from 20 to 35

 Dataset

 2, 135 movies released between 2006 and 2011  Movie

content – title, poster, plot keywords, cast, director, summary – crawled from the Internet Movie Database (IMDb)

 Vocabulary of 32, 583 plot keywords  Average: 12.33 keywords/item

Experimental Evaluation (user study): Design of the experiment

74

 Between-subjects controlled experiment

 20 users randomly assigned to test RWR-KI  20 users randomly assigned to test RANDOM (control

group), a baseline inspired by the blind luck principle which produces random suggestions that showed surprisingly good performance in the 1st In-vitro experiment

 Procedure

 Users interact with a web application

– shows details of movies – displays 5 recommendations (movie poster & title) per user

 Recommended items displayed 1 at a time

Web application

75

Experimental Evaluation (user study): Design of the experiment

76

 Procedure

 2 binary questions to assess user acceptance

– “Did you know this movie?” “Have you ever heard about this movie?” (unexpectedness) – “Do you like this movie?” (relevance) – (NO,YES) answers  serendipitous recommendation

 Video started when a movie is recommended to the user

and stopped when the answers to the 2 questions are collected

 5 videos per user  Noldus FaceReader™ used to analyze videos and assess

user emotional response when exposed to recommendations

Experimental Evaluation (user study): Design of the experiment

77

 Questionnaire analysis

 Quality of RWR-KI and RANDOM  Metrics

Relevance@N = #relevant_items/N Unexpectedness@N = #unexpected_items/N Serendipity@N = #serendipitous_items/N = #(relevant_items unexpected_items)/N N = size of the recommendation list

Experimental Evaluation (user study): Design of the experiment

78

 Questionnaire analysis

 ResQue model (Chen et al. 2010)

– category: Perceived System Qualities – sub-category: Quality of Recommended Items – Relevance = perceived accuracy – Unexpectedness = novelty

(Chen et al. 2010) L. Chen, P. Pu, A User-Centric Evaluation Framework of Recommender Systems, in: B.P. Knijnenburg, L. Schmidt- Thieme, D. Bollen (Eds.), Proceedings of the ACM RecSys 2010 Workshop on User-Centric Evaluation of Recommender Systems and Their Interfaces (UCERSTI), CEUR Workshop Proceedings 612, 14-21, CEUR-WS.org, 2010.

Experimental Evaluation (user study): Results

79

 Questionnaire analysis

 Serendipity: RWR-KI outperforms RANDOM  Statistically significant differences (Mann-Whitney U test,

p<0.05)



~ Half

• f

the recommendations are deemed serendipitous!

 RWR-KI: a better Relevance-Unexpectedness trade-off  RANDOM: more unbalanced towards Unexpectedness

Experimental Evaluation (user study): Results

80

 Questionnaire analysis: distribution of serendipitous items within Top-5 lists

 Almost all users (19 out of 20) received 1 serendipitous

suggestions

 Most of RWR-KI lists: 2-3 serendipitous items  Most of RANDOM lists: 1-2 serendipitous items

Experimental Evaluation (user study): Results

81

 Analysis of user emotions  Hypothesis: users’ facial expressions convey a mixture

• f

emotions that helps to measure the perception of serendipity of recommendations  Serendipity associated to surprise and happiness  ResQue model: attractiveness  200 videos (40 users x 5 recommendations)  41 videos filtered out (< 5 seconds)   159 videos, FaceReader™ computed the distribution of detected emotions + duration (emotions lasting <1 sec.)

Circumplex model

 Maps basic emotions dimensional model

Arousal Valence

high negative positive low

neutr al sadne ss fear disgu st surpri se joy anger

 Frequency analysis of user emotions associated to serendipitous suggestions (69 videos=81–12)

 Surprise: 17% RWR-KI vs 9% RANDOM  Happiness: 14% RWR-KI vs 9% RANDOM  RWR-KI

produces more serendipitous suggestions than RANDOM! (confirm questionnaires results)

 High values of negative emotions (sadness and anger); why?

Experimental Evaluation (user study): Results

83 39 videos 30 videos

Experimental Evaluation (user study): Results

84

 Frequency analysis of user emotions associated to non-serendipitous suggestions (90 videos=119–29)

 General decrease of surprise and happiness  High values of negative emotions (sadness and anger), also in

this case

 Explanation: Negative emotions due to the fact that users assumed troubled expressions since they were very concentrated on the task

39 videos 51 videos

Experimental Evaluation (user study): Conclusions

85

 Positive emotions: marked difference between RWR-KI and RANDOM  Positive emotions: marked difference between serendipitous recommendations and non-serendipitous ones  Agreement between questionnaires (explicit feedback) & facial expressions/emotions (implicit feedback)  Emotions can help to assess the actual perception of serendipity  A step forward to the creation of a ground truth for evaluation purposes

Outline

 Background  The role of Personality in Decision Making and Recommender Systems

 Models  Acquisition  Personality and Decision Making  Personality in RecSys – examples

 The role of Emotions in Decision Making and Recommender Systems

 Models  Acquisition  Emotions and Decision Making  Emotions in RecSys – examples

 Focus: Emotions as Implicit Feedback for evaluation purposes  Conclusions and take away notes

86

Publishing opportunities

 UMUAI Special Issue on Personality in Personalized Systems (Tkalčič, Quercia, Graf) : 1. December 2014  UMUAI Special Issue on Physiology in Personalized Systems (Tkalčič, Fairclough, Conati, Valjamae): mid 2015

Concluding Remarks, Take away notes & Challenges

 Wrap-up:



DM = Rational + Emotional



DM is related to personality



Various models (of emotions and personality)



Acquisition is not perfect



Variety of approaches in RS  Future:



Novel RS metric required (that take into account affect and personality)



Watch out for better acquisition methods:

– affective computing community, – personality computing, – social signal processing – New devices (e.g. google glass + Fraunhofer Shore)



Explore the usage of personality and emotions:

– Context – Personalized feedback acquisition (Feedback interpretation) – Visualization (browsing styles, diversity…) – Group modeling – Preference modeling – Explore the „reasons“ for consumption (uses and gratification theory)



Privacy issues (e.g. Facebook experiment) … not addressed here

Thanks…Questions?

“Data scientists will be the rock stars of the Big Data era”

(www.greenplum.com)

Semantic Web Access and Personalization research group

http://www.di.uniba.it/~swap

Pierpaolo Basile Marco de Gemmis Leo Iaquinta Piero Molino Fedelucio Narducci Annalina Caputo Giuseppe Ricci Pasquale Lops Cataldo Musto Giovanni Semeraro Markus Schedl Bruce Ferwerda

http://cp.jku.at

Gregor Geršak Janko Drnovšek Andrej Košir Ante Odić Tomaž Vodlan

References

 (Basile et al. 2014) P. Basile, M. de Gemmis, P. Lops, G. Semeraro. Solving a Complex Language Game by using Knowledge-based Word Associations Discovery. IEEE Transactions

• n

Computational Intelligence and AI in Games, 2014 (in press).  (Chen et al. 2010) L. Chen, P. Pu, A User-Centric Evaluation Framework of Recommender Systems, in: B.P. Knijnenburg, L. Schmidt-Thieme, D. Bollen (Eds.), Proceedings of the ACM RecSys 2010 Workshop on User-Centric Evaluation of Recommender Systems and Their Interfaces (UCERSTI), CEUR Workshop Proceedings 612, 14-21, CEUR-WS.org, 2010.  (de Gemmis et al. 2014) M. de Gemmis, P. Lops, G. Semeraro. An Investigation on the Serendipity Problem in Recommender Systems. Submitted manuscript, 2014.  (Ekman 1999) P. Ekman, Basic Emotions, in T. Dalgleish, M.J. Power (Eds.), Handbook of Cognition and Emotion, 45–60, John Wiley & Sons, 1999.  (Herlocker et al. 2004) Herlocker, L., Konstan, J.A., Terveen, L.G., Riedl, J.T.: Evaluating Collaborative Filtering Recommender Systems. ACM Transactions on Information Systems 22(1): 5–53, 2004.  (Kramer et al. 2014) Kramer, Adam D. I.; Guillory, Jamie E.; Hancock, Jeffrey T. Experimental evidence of massive-scale emotional contagion through social networks. Proceedings of the National Academy of Sciences of the United States of America, vol. 11, issue 29, 8788-8790, 2014.  (Langner et al. 2010) O. Langner, R. Doetsch, G. Bijlstra, D.H.J. Wigboldus, S.T. Hawk, A. van

• Knippenberg. Presentation and Validation of the Radboud Faces Database, Cognition and

Emotion 24(8), 1377-1388, 2010.  (Lauw et al. 2010) Lauw, H.W., Schafer, J.C., Agrawal, R., & A. Ntoulas. Homophily in the Digital World: A LiveJournal Case Study. IEEE Internet Computing 14(2):15-23, March-April 2010.  (Lovasz 1996) L. Lovasz. Random Walks on Graphs: a Survey. Combinatronics 2:1–46, 1996.  (McNee et al. 2006) S. M. McNee, J. Riedl, and J. A. Konstan. Being accurate is not enough: How accuracy metrics have hurt recommender systems. In CHI ’06 Extended Abstracts on Human Factors in Computing Systems, CHI EA ’06, pages 1097–1101, ACM, New York, NY, USA, 2006.

References

 (Murakami et al. 2008) T. Murakami, K. Mori, R. Orihara, Metrics for Evaluating the Serendipity

• f Recommendation Lists, in K. Satoh, A. Inokuchi, K. Nagao, T. Kawamura (Eds.), New

Frontiers in Artificial Intelligence, Lecture Notes in Computer Science 4914, pp. 40–46, Springer, 2008.  (Pariser 2011) E. Pariser. The Filter Bubble: What the Internet Is Hiding from You. Penguin Group, May 2011.  (Roy 2001) Arundhati Roy. Power Politics. South End Press, January 2001.  (Semeraro et al. 2012) G. Semeraro, M. de Gemmis, P. Lops, P. Basile. An Artificial Player for a Language Game. IEEE Intelligent Systems 27(5): 36-43, 2012.  (Toms 2000) E. Toms. Serendipitous Information Retrieval. Proceedings of the First DELOS Network of Excellence Workshop on Information Seeking, Searching and Querying in Digital Libraries, Zurich, Switzerland: European Research Consortium for Informatics and Mathematics, 2000.  (Zuckerman 2008) E. Zuckerman. Homophily, serendipity, xenophilia. April 25, 2008. www.ethanzuckerman.com/blog/2008/04/25/homophily-serendipity-xenophilia/

References

 Cain, S. (2013). Quiet: The Power of Introverts in a World That Can’t Stop Talking. Broadway Books.  (McCraMcCrae, R. R., & John, O. P. (1992). An Introduction to the Five-Factor Model and its Applications. Journal of Personality, 60(2), p175 – 215.  J.L Holland: Making vocational choices, Prentice-Hall, Englewood Cliffs (1973)  http://www.gamasutra.com/view/feature/134842/personality_and_play_styles_a_.php  El-Bishouty, M. M., Chang, T.-W., Graf, S., & Chen, N.-S. (2014). Smart e-course recommender based on learning styles. Journal of Computers in Education, 1(1), 99–111. doi:10.1007/s40692-014-0003-0  Furnham, A. (1996). The big five versus the big four: the relationship between the Myers-Briggs Type Indicator (MBTI) and NEO-PI five factor model of personality. Personality and Individual Differences, 21(2), 303–307. doi:10.1016/0191-8869(96)00033-5  http://homepage.psy.utexas.edu/HomePage/Faculty/Gosling/tipi%20site/tipi.htm  Gosling, S. D., Rentfrow, P. J., & Swann, W. B. (2003). A very brief measure of the Big-Five personality domains. Journal of Research in Personality, 37(6), 504–528. doi:10.1016/S0092-6566(03)00046-1  Kosinski, M., Stillwell, D., & Graepel, T. (2013). Private traits and attributes are predictable from digital records

• f

human behavior. Proceedings

• f

the National Academy

• f

Sciences, 2–5. doi:10.1073/pnas.1218772110  Golbeck, J., Robles, C., & Turner, K. (2011). Predicting personality with social media. Proceedings of the 2011 Annual Conference Extended Abstracts on Human Factors in Computing Systems - CHI EA ’11, 253. doi:10.1145/1979742.1979614  Quercia, D., Kosinski, M., Stillwell, D., & Crowcroft, J. (2011). Our Twitter Profiles, Our Selves: Predicting Personality with Twitter. In 2011 IEEE Third Int’l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing (pp. 180–185). IEEE. doi:10.1109/PASSAT/SocialCom.2011.26  Shen, J., Brdiczka, O., & Liu, J. (2013). Understanding Email Writers: Personality Prediction from Email

• Messages. User Modeling, Adaptation, and Personalization, 318–330. doi:10.1007/978-3-642-38844-6_29

 Nowson, S., & Oberlander, J. (2007). Identifying more bloggers: Towards large scale personality classification

• f

personal weblogs. International Conference

• n

Weblogs and Social Media. Retrieved from http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.64.2021  Kosinski, M., Stillwell, D., & Graepel, T. (2013). Private traits and attributes are predictable from digital records

• f

human behavior. Proceedings

• f

the National Academy

• f

Sciences, 2–5. doi:10.1073/pnas.1218772110

References

 Pečjak, S., & Košir, K. (2007). Personality, motivational factors and difficulties in career decision-making in secondary school students. Psihologijske Teme, 16, 141–158.  Deniz, M. (2011). An Investigation of Decision Making Styles and the Five-Factor Personality Traits with Respect to Attachment Styles. Educational Sciences: Theory and Practice, 11(1), 105–114.  Mann, L., Burnett, P., Radford, M., & Ford, S. (1997). The Melbourne Decision Making Questionnaire: An instrument for measuring patterns for coping with decisional conflict. Journal of Behavioral Decision Making, 10(1), 1–19.  McCrae, R. R., & Costa, P. T. (1989). Reinterpreting the Myers-Briggs Type Indicator from the perspective of the five-factor model of personality. Journal of Personality, 57(1), 17–40. doi:10.1111/1467-6494.ep8972588  Tkalcic, M., Kunaver, M., Košir, A., & Tasic, J. (2011). Addressing the new user problem with a personality based user similarity measure. DEMRA 2011, UMMS 2011  Elahi, M., Braunhofer, M., Ricci, F., & Tkalcic, M. (2013). Personality-based active learning for collaborative filtering recommender systems. AI*IA 2013: Advances in Artificial Intelligence, 360–371. doi:10.1007/978-3- 319-03524-6_31  Wu, W., Chen, L., & He, L. (2013). Using personality to adjust diversity in recommender systems. Proceedings

• f

the 24th ACM Conference

• n

Hypertext and Social Media

• HT

’13, (May), 225–229. doi:10.1145/2481492.2481521  Rentfrow, P. J., & Gosling, S. D. (2003). The do re mi’s of everyday life: The structure and personality correlates

• f

music preferences. Journal

• f

Personality and Social Psychology, 84(6), 1236–1256. doi:10.1037/0022-3514.84.6.1236  Recio-Garcia, J. A., Jimenez-Diaz, G., Sanchez-Ruiz, A. A., & Diaz-Agudo, B. (2009). Personality aware recommendations to groups. In Proceedings of the third ACM conference on Recommender systems - RecSys ’09 (p. 325). New York, New York, USA: ACM Press. doi:10.1145/1639714.1639779  Quijano-Sanchez, L., Recio-Garcia, J. a., & Diaz-Agudo, B. (2010). Personality and Social Trust in Group

• Recommendations. 2010 22nd IEEE International Conference on Tools with Artificial Intelligence, (c), 121–
• 126. doi:10.1109/ICTAI.2010.92

 Kompan, M., & Bieliková, M. (2014). Social Structure and Personality Enhanced Group Recommendation. EMPIRE 2014: Emotions and Personality in Personalized Services.  Ferwerda, Schedl, Tkalčič (2014), Personality & Emotional States: Understanding User’s Music Listening Needs to Enhance Recommender Systems, submitted to CHI 2015

References

 Ferwerda, Yang, Schedl, Tkalčič (2014), Personality Traits Predict Music Category Preferences, submitted to CHI 2015  Tkalčič, M., Odić, A., & Košir, A. (2013). The impact of weak ground truth and facial expressiveness on affect detection accuracy from time-continuous videos of facial expressions. Information Sciences, 249, 13–23. doi:10.1016/j.ins.2013.06.006  Tkalcic, M., Odic, A., Kosir, A., & Tasic, J. (2013). Affective Labeling in a Content-Based Recommender System for Images. IEEE Transactions on Multimedia, 15(2), 391–400. doi:10.1109/TMM.2012.2229970  Hasan, M., Rundensteiner, E., & Agu, E. (n.d.). EMOTEX : Detecting Emotions in Twitter Messages., SocialCom2014  Loewenstein, G., & Lerner, J. S. (2003). The role of affect in decision making. In R. Davidson, K. Scherer & H. Goldsmith (Eds.), Handbook of affective science (pp. 619-642). New York: Oxford University Press.  Slovic, P., Finucane, M., Peters, E., & MacGregor, D. G. (2002). The affect heuristic. In T. Gilovich, D. Griffin, &

• D. Kahneman (Eds.), Heuristics and biases: The psychology of intuitive judgment. Cambridge: Cambridge

University, Press.  Damasio, A.R. (1996) "The Somatic Marker Hypothesis and the Possible Functions of the Prefrontal Cortex". Philosophical Transactions 351 (1346): 1413–1420,  Damasio, A.R. (1994) Descartes' Error: Emotion, Reason, and the Human Brain, Putnam, 1994.  Tkalčič, M., Košir, A., Tasič, J., & Kunaver, M. (2011). Affective recommender systems : the role of emotions in recommender systems. Proceedings

• f

the RecSys 2011 Workshop

• n

Human Decision Making in Recommender Systems (Decisions@RecSys’11), 9–13. Retrieved from http://ceur-ws.org/Vol- 740/UMMS2011_paper6.pdf  [Kaminskas2011] Marius Kaminskas and Francesco Ricci. 2011. Location-adapted music recommendation using tags. Proceedings of UMAP '11, Springer-Verlag, Berlin, Heidelberg, 183-194.  [Zheng2013] Yong Zheng, Bamshad Mobasher, Robin D. Burke: The Role of Emotions in Context-aware

• Recommendation. Decisions@RecSys 2013: 21-28

References

 [Wang2013] Licai Wang, Xiangwu Meng, Yujie Zhang, and Yancui Shi. 2010. New approaches to mood-based hybrid collaborative filtering. In Proc. of the Workshop on Context-Aware Movie Recommendation (CAMRa '10). ACM, New York, NY, USA, 28-33.  [Shi2003] Shi, Y., Larson, M., and Hanjalic, A. 2010. Mining mood-specific movie similarity with matrix factorizationfor context-aware recommendation. In Proceedings of the Workshop on Context-Aware Movie Recommendation (CAMRa’10). ACM, New York, NY, 34–40.  Tkalčič, M., Burnik, U., & Košir, A. (2010). Using affective parameters in a content-based recommender system for images. User Modeling and User-Adapted Interaction, 20(4), 279–311. doi:10.1007/s11257-010-9079-z  Vodlan, T., Tkalčič, M., & Košir, A. (2014). The impact of hesitation, a social signal, on a user’s quality of experience in multimedia content retrieval. Multimedia Tools and Applications. doi:10.1007/s11042-014- 1933-2  Tkalčič, M., Košir, A., & Tasič, J. (2013). The LDOS-PerAff-1 corpus of facial-expression video clips with affective, personality and user-interaction metadata. Journal on Multimodal User Interfaces, 7(1-2), 143–155. doi:10.1007/s12193-012-0107-7  Košir, A., Odić, A., Kunaver, M., Tkalčič, M., & Tasič, J. F. (2011). Database for contextual personalization. Elektrotehniški Vestnik, 78(5), 270–274.

SLIDE A SUPPORTO

Concluding Remarks, Take away notes & Challenges

 DM = Rational + Emotional  New metrics, evaluation settings and measures that exploit the user’s emotional state to create a ground truth for evaluation purposes

 Google Glass: real-time emotion detection  The dark side: Facebook experiment on massive emotion

contagion (Kramer et al. 2014)

 “personalized” models for the acquisition of affective feedback

Experimental Evaluation (in-vitro): Dataset

98

 A subset of HETREC2011-MOVIELENS-2K  Freely downloadable at http://grouplens.org/datasets/hetrec-2011  Dataset of user-movie ratings

 855,598 ratings, 2,113 users  10,197 items (movies)  Discrete rating between 0.5 and 5.0 (step 0.5 – 10-point Likert

scale)

 Sparsity 96.03%  Movies content – plot keywords & summary – crawled from the

Internet Movie Database (IMDb)

The Serendipity Problem

 Homophily: the tendency to surround ourselves by like-minded people (Zuckerman 2008) E. Zuckerman. Homophily, serendipity, xenophilia.

April 25, 2008. www.ethanzuckerman.com/blog/2008/04/25/homophily-serendipity-xenophilia/

• pinions taken to extremes

cultural impoverishment threat for biodiversity?

Homophily in the digital world

• in the physical world, one of the strongest sources of homophily is

locality, due to geographic proximity, family ties, and

• rganizational factors (school, work, etc.)
• in the digital world, physical locality is less important. Other

factors, such as common interests, might play a central role 2 main questions:

• Are two users more likely to be friends if they share common

interests?

• Are two users more likely to share common interests if they are

friends? In (Lauw et al. 2010), the answer to both questions is YES

(Lauw et al. 2010) Lauw, H.W., Schafer, J.C., Agrawal, R., & A. Ntoulas. Homophily in the Digital World: A LiveJournal Case

• Study. IEEE Internet Computing 14(2):15-23, March-April 2010.

The Homophily Trap in RecSys

 Does homophily hurt RS?

 try to tell Amazon that you liked the movie “War

Games”…

(Zuckerman 2008) E. Zuckerman. Homophily, serendipity, xenophilia. April 25, 2008. www.ethanzuckerman.com/blog/2008/04/25/homophily-serendipity-xenophilia/

The Homophily Trap in RecSys

Recommendations by other GEEKS!

The Homophily Trap in RecSys… …Harry Potter for ever?

Spreading Activation Network

alien

Dic1 Dic2 Wiki1

stranger

space

• utsider

foreigner

Wiki2

extraterr. being

future ufo battle

Dic3 Dic4 Wiki3

war

Wiki4

sea boat game conflict enemy army

stalingrad

scott weaver

0.67 0.72 0.85 0.38 0.51 0.65 0.69 0.71 invasion

story navy

0.42 0.20 0.26 0.44 0.32 0.93 0.34 0.93 0.76 0.32 0.98 0.98 0.15 0.12 1.12 1.12 1.01 0.22 0.30 0.99 0.77 0.78 0.78 0.88 0.88 0.68 0.34 0.34 1.01

life

The role of emotions in decision making: the traditional “influence-on” view

 Choosing is seen as a rigorous cognitive process that estimates the consequences of various alternative choices

 Satisfaction  Time invested  Justifiability

 Emotions are considered as external forces influencing an otherwise non-emotional process

 irrational occurrences that may alter reasoning

105

Loewenstein, G., & Lerner, J. S. (2003). The role of affect in decision making. In R. Davidson, K. Scherer & H. Goldsmith (Eds.), Handbook of affective science (pp. 619-642). New York: Oxford University Press.

Which Role for Emotions in Recommender Systems Research?

106

 How can affective information be exploited by recommendation algorithms that take into account the ways in which affect actually influences the decision process?  Is the emotional response useful to assess user satisfaction?

Emotion-aware Recommender Systems

107

 Emotions and feelings seen as in the “influence-on” view

 Affective information is not directly included

in the preference model

 Emotions as contextual variables  Typical emotional contexts are related to user

mood or feeling (e.g. the mood after seeing a movie)

 Empirical results show that using emotional contextual information can improve (movie, music) recommendations

Content application

Entry mood Detec t entry mood Give conte nt Exit mood

time Entry stage Consumption stage Exit stage

Give recommendati

• ns

choice

• Context
• Diversity

Emotions in the consumption chain

Tkalčič, M., Košir, A., Tasič, J., & Kunaver, M. (2011). Affective recommender systems : the role of emotions in recommender systems. Proceedings of the RecSys 2011 Workshop on Human Decision Making in Recommender Systems (Decisions@RecSys’11), 9–13. Retrieved from http://ceur-ws.org/Vol-740/UMMS2011_paper6.pdf

Content application

Entry mood Detec t entry mood Give conte nt Content-induced affective state Observe user

time Entry stage Consumption stage Exit stage

Give recommendati

• ns

choice

• Affective tagging
• Affective user profiles

Emotions in the consumption chain

Tkalčič, M., Košir, A., Tasič, J., & Kunaver, M. (2011). Affective recommender systems : the role of emotions in recommender systems. Proceedings of the RecSys 2011 Workshop on Human Decision Making in Recommender Systems (Decisions@RecSys’11), 9–13. Retrieved from http://ceur-ws.org/Vol-740/UMMS2011_paper6.pdf

Content application

Entry mood Detec t entry mood Give conte nt Content-induced affective state Exit mood Observe user

time Entry stage Consumption stage Exit stage

Give recommendati

• ns

choice Detec t exit mood

• Implicit feedback
• Evaluation metrics

(user satisfaction)

Emotions in the consumption chain

Tkalčič, M., Košir, A., Tasič, J., & Kunaver, M. (2011). Affective recommender systems : the role of emotions in recommender systems. Proceedings of the RecSys 2011 Workshop on Human Decision Making in Recommender Systems (Decisions@RecSys’11), 9–13. Retrieved from http://ceur-ws.org/Vol-740/UMMS2011_paper6.pdf

Emotions as Contexts in Context-aware Recommender Systems (II)

111

 Mood-based user-based CF [Wang2013]

 Multiple-step nearest neighbors search working on both

ratings and movie mood

 Mood helps to find more accurate nearest neighbors

 Mining mood-specific movie similarity with matrix factorization [Shi2003]

 Novel mood-specific movie similarity compared to general

mood-based similarity

 Using a specific mood tag is preferable over using general

mood tags

 Learning latent movie features wrt a specified mood

increase accuracy

[Wang2013] Licai Wang, Xiangwu Meng, Yujie Zhang, and Yancui Shi. 2010. New approaches to mood-based hybrid collaborative filtering. In Proc. of the Workshop on Context-Aware Movie Recommendation (CAMRa '10). ACM, New York, NY, USA, 28-33. [Shi2003] Shi, Y., Larson, M., and Hanjalic, A. 2010. Mining mood-specific movie similarity with matrix factorizationfor context-aware recommendation. In Proceedings of the Workshop on Context- Aware Movie Recommendation (CAMRa’10). ACM, New York, NY, 34–40.