Affect- and Personality-based Recommender Systems Part II: - - PowerPoint PPT Presentation

▶
affect and personality based recommender systems
SMART_READER_LITE
LIVE PREVIEW

Affect- and Personality-based Recommender Systems Part II: - - PowerPoint PPT Presentation

Nov 30, 2022 328 likes •897 views

Affect- and Personality-based Recommender Systems Part II: Acquisition, Usage in Recommender Systems Marko Tkali, Free University of Bozen-Bolzano ACM Summer School on Recommender Systems 2017 Marko Tkali,

slide-1
SLIDE 1

Affect- and Personality-based Recommender Systems

Part II: Acquisition, Usage in Recommender Systems

Marko Tkalčič, Free University of Bozen-Bolzano

ACM Summer School on Recommender Systems 2017 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 1/53

slide-2
SLIDE 2

Table of Contents

Recap Acquisition of Personality Usage of personality in recommender systems Acquisition of Emotions Usage of emotions in recommender systems Conclusion Hands-on User Study

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 2/53

slide-3
SLIDE 3

Emotions vs Personality

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 3/53

slide-4
SLIDE 4

Measuring Emotions and Personality

TIPI: I see myself as:

  • 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.

Self-reporting is intrusive There is a need for unobtrusive ways of measuring E&P

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 4/53

slide-5
SLIDE 5

Report

  • N = 42
  • 32M, 8F, 2 unknown

Ext Agr Con EmS Ope Age Mean 3,61 3,75 5,08 3,27 5,06 28,72 SD 1,51 1,15 1,21 1,44 1,22 4,97 Male norms 21-30 Mean 3,73 4,50 4,57 4,64 5,49 SD 1,54 1,20 1,39 1,46 1,13

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 5/53

slide-6
SLIDE 6

Table of Contents

Recap Acquisition of Personality Usage of personality in recommender systems Acquisition of Emotions Usage of emotions in recommender systems Conclusion Hands-on User Study

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 6/53

slide-7
SLIDE 7

Personality Detection

Our online behaviour is influenced by our personality.

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 7/53

slide-8
SLIDE 8

Personality Detection

Our online behaviour is influenced by our personality. Hence, our traces in social media should reflect our personality.

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 7/53

slide-9
SLIDE 9

Personality Detection

Our online behaviour is influenced by our personality. Hence, our traces in social media should reflect our personality. It is enough to acquire personality once.

  • Twitter (Golbeck et al., 2011, Quercia et al., 2011)
  • Facebook, (Golbeck et al., 2011, Kosinski et al., 2013)
  • Instagram (Skowron et al., 2016)

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 7/53

slide-10
SLIDE 10

Personality from Twitter

  • N=335
  • features
  • log(num of followers)
  • log(num of followees)
  • log(num of times listed)
  • Klout score (num of clicks, num of retweets)
  • TIME (twitter and facebook followers)
  • M5 rules regressor
  • personality on the scale 1-5

References

Quercia, D., Kosinski, M., Stillwell, D., and Crowcroft, J. (2011). Our twitter profiles, our selves: Predicting personality with twitter. In Proceedings - 2011 IEEE International Conference on Privacy, Security, Risk and Trust and IEEE International Conference on Social Computing, PASSAT/SocialCom 2011 (pp. 180–185). IEEE. https://doi.org/10.1109/PASSAT/SocialCom.2011.26 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 8/53

slide-11
SLIDE 11

Kosinki - personality from FB

  • personality prediction from Facebook

References

Kosinski, M., Stillwell, D., and Graepel, T. (2013). Private traits and attributes are predictable from digital records of human behavior. Proceedings of the National Academy of Sciences of the United States of America, 110(15), 5802–5. https://doi.org/10.1073/pnas.1218772110 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 9/53

slide-12
SLIDE 12

Kosinki - personality from FB

  • Prediction accuracy as Pearson

correlation coefficient

  • all correlations significant at p < 0.001
  • transparent bars = questionnaire’s

baseline accuracy (test–retest reliability)

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 10/53

slide-13
SLIDE 13

Kosinki - personality from FB

Selected most predictive likes for openness

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 11/53

slide-14
SLIDE 14

Personality from Instagram

  • N=113 (AMT)
  • 22398 pictures
  • BFI
  • features
  • low-level image features

(Hue-Value-Saturation)

  • filters
  • presence of people

References

Skowron, M., Ferwerda, B., Tkalčič, M., and Schedl, M. (2016). Fusing Social Media Cues : Personality Prediction from Twitter and

  • Instagram. WWW’16 Companion, 2–3. https://doi.org/10.1145/2872518.2889368

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 12/53

slide-15
SLIDE 15

Linguistic features

  • (Farnadi et al., 2016) compared Facebook, Twitter and Youtube
  • small differences between classifiers
  • major differences between linguistic features:
  • 81 LIWC features
  • 66 SPLICE features
  • 2 SentiStrength features
  • 14 MRC
  • 8 NRC
  • LIWC (Linguistic Inquiry and Word Count) features best predictors

References

Farnadi, G., Sitaraman, G., Sushmita, S., Celli, F., Kosinski, M., Stillwell, D., . . . De Cock, M. (2016). Computational personality recognition in social media. User Modeling and User-Adapted Interaction, (Special Issue on Personality in Personalized Systems). https://doi.org/10.1007/s11257-016-9171-0 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 13/53

slide-16
SLIDE 16

IBM Watson

Demo time :-) https://personality-insights-livedemo.mybluemix.net/#your-twitter-panel References

Srivastava, Abhishek. "Gray Sheep, Influential Users, User Modeling and Recommender System Adoption by Startups." Proceedings of the 10th ACM Conference on Recommender Systems. ACM, 2016. Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 14/53

slide-17
SLIDE 17

Table of Contents

Recap Acquisition of Personality Usage of personality in recommender systems Acquisition of Emotions Usage of emotions in recommender systems Conclusion Hands-on User Study

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 15/53

slide-18
SLIDE 18

Personality 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) References

Ferwerda, B., Schedl, M., and Tkalcic, M. (2015). Personality and Emotional States : Understanding Users ’ Music Listening Needs. In

  • A. Cristea, J. Masthoff, A. Said, and N. Tintarev (Eds.), UMAP 2015 Extended Proceedings.

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 16/53

slide-19
SLIDE 19

Personality and music browsing styles

  • personality is correlated with music browsing styles

References

Ferwerda, B., Yang, E., Schedl, M., and Tkalčič, M. (2015). Personality Traits Predict Music Taxonomy Preferences. In Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems - CHI EA ’15 (pp. 2241–2246). https://doi.org/10.1145/2702613.2732754 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 17/53

slide-20
SLIDE 20

Personality and Ratings

  • movielens
  • N=1840

References

Karumur, R. P., Nguyen, T. T., and Konstan, J. A. (2016). Exploring the Value of Personality in Predicting Rating Behaviors. In Proceedings of the 10th ACM Conference on Recommender Systems - RecSys ’16 (pp. 139–142). New York, New York, USA: ACM

  • Press. https://doi.org/10.1145/2959100.2959140

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 18/53

slide-21
SLIDE 21

Personality as user similarity

  • new user problem
  • N = 52
  • images = 70
  • neighborhood-based RS: Euclidian distance −1

References

Tkalčič, M., Kunaver, M., Košir, A., and Tasič, J. (2011). Addressing the new user problem with a personality based user similarity

  • measure. In F. Ricci, G. Semeraro, M. de Gemmis, P. Lops, J. Masthoff, F. Grasso, J. Ham (Eds.), Joint Proceedings of the Workshop
  • n Decision Making and Recommendation Acceptance Issues in Recommender Systems (DEMRA 2011) and the 2nd Workshop on User

Models for Motivational Systems: The affective and the rational routes to persuasion (UMMS 2011). Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 19/53

slide-22
SLIDE 22

Personality as user similarity

  • N = 113
  • 646 songs
  • TIPI
  • user similarities (Pearson CC)
  • item-based
  • personality-based

References

Hu, R., and Pu, P. (2010). Using Personality Information in Collaborative Filtering for New Users. In Proceedings of the 2nd ACM RecSys’10 Workshop on Recommender Systems and the Social Web (pp. 17–24). Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 20/53

slide-23
SLIDE 23

Personality and Diversity

  • within subject N=52
  • movies
  • diversity per: genre, director, country, release time, actor
  • rules from a previous study
  • High Level of Openness is linked to high need for diversity w.r.t. —actor/actress
  • Low Level of Conscientiousness is correlated with high need for the overall diversity

References

Wu, W., Chen, L., and 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. Chen, L., Wu, W., and He, L. (2013). How personality influences users’ needs for recommendation diversity? CHI ’13 Extended Abstracts on Human Factors in Computing Systems on - CHI EA ’13, 829. https://doi.org/10.1145/2468356.2468505 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 21/53

slide-24
SLIDE 24

Personality in Matrix Factorization

  • in (Elahi et al., 2013) and (Fernández-Tobías, 2016)
  • injection of personality factors in MF as additional (latent) features (a la SVD++)

rui = qi(pu +

  • a∈A(u)

ya)

  • personality u = (2.3, 4.0, 3.6, 5.0, 1.2) maps to A(u) = {ope2, con4, ext4, agr5,

neu1}.

  • (Fernández-Tobías, 2016) is a very comprehensive paper
  • iMF = (Hu et al., 2008)

References

Elahi, M., Braunhofer, M., Ricci, F., and Tkalčič, M. (2013). Personality-based active learning for collaborative filtering recommender

  • systems. In M. Baldoni, C. Baroglio, G. Boella, and O. Micalizio (Eds.), AI*IA 2013: Advances in Artificial Intelligence (pp. 360–371).

Fernández-Tobías, I., Braunhofer, M., Elahi, M., Ricci, F., and Cantador, I. (2016). Alleviating the new user problem in collaborative filtering by exploiting personality information. User Modeling and User-Adapted Interaction, 26(2), 1–35. https://doi.org/10.1007/s11257-016-9172-z Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 22/53

slide-25
SLIDE 25

UMUAI Special Issue

  • UMUAI, June 2016
  • Special Issue on Personality in Personalized Systems
  • Issue Editors:
  • Marko Tkalcic,
  • Daniele Quercia,
  • Sabine Graf

References

Tkalčič, M., Quercia, D., and Graf, S. (2016). Preface to the special issue on personality in personalized systems. User Modeling and User-Adapted Interaction, 26(2–3), 103–107. https://doi.org/10.1007/s11257-016-9175-9 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 23/53

slide-26
SLIDE 26

Other uses of personality in recommender systems

  • personality and cross domain (Cantador et al., 2013)
  • personality in group RS (Masthoff, 2015)
  • Amazon MF + personality from Twitter (Adamopoulos and Todri, 2015)

References

Cantador, I., Fernández-tobías, I., and Bellogín, A. (2013). Relating Personality Types with User Preferences in Multiple Entertainment

  • Domains. EMPIRE 1st Workshop on “Emotions and Personality in Personalized Services”, 10. June 2013, Rome.

Masthoff, J. (2015). Group Recommender Systems: Aggregation, Satisfaction and Group Attributes. In Recommender Systems Handbook (Vol. 54, pp. 743–776). Boston, MA: Springer US. Adamopoulos, Panagiotis, and Vilma Todri. "Personality-Based Recommendations: Evidence from Amazon. com." RecSys Posters. 2015. Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 24/53

slide-27
SLIDE 27

Table of Contents

Recap Acquisition of Personality Usage of personality in recommender systems Acquisition of Emotions Usage of emotions in recommender systems Conclusion Hands-on User Study

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 25/53

slide-28
SLIDE 28

Multimodal Emotion Detection

  • Emotions consist of a coordinated set of responses (verbal, physiological,

behavioral, and neural mechanisms)

  • These responses can be used to measure the emotions.
  • Affective Computing

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 26/53

slide-29
SLIDE 29

Overview

  • modalities
  • audio
  • language
  • visual - videos of faces (action units)
  • physiology
  • brain signals
  • target emotion
  • discrete (classification)
  • continuous (regression)

References

Schuller, B. W. (2016). Acquisition of Affect. In M. Tkalčič, B. De Carolis, M. de Gemmis, A. Odić, and A. Košir (Eds.), Emotions and Personality in Personalized Services: Models, Evaluation and Applications (pp. 57–80). Cham: Springer International Publishing. Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 27/53

slide-30
SLIDE 30

Lie to me

  • TV series
  • main character (Tim Roth) based on Paul Ekman

[part1.avi]

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 28/53

slide-31
SLIDE 31

Problems with emotion detection

  • perfect illumination [AU1_2_5s.mpg]
  • [video_3_divx.avi,video_100_divx.avi]

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 29/53

slide-32
SLIDE 32

Problems with emotion detection

  • perfect illumination [AU1_2_5s.mpg]
  • [video_3_divx.avi,video_100_divx.avi]

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 29/53

slide-33
SLIDE 33

Unobtrusive Emotion Detection from Facial Videos

  • 2 datasets:
  • Posed (Kanade Cohn)
  • Spontaneous (LDOS-PerAff-1)
  • video streams of facial expressions as

responses to visual stimuli

  • distinct classes
  • Gabor features
  • kNN classifier
  • 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

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 30/53

slide-34
SLIDE 34

Academic semi-solutions for emotion recognition

  • many research groups offer

their code

  • usual prototype-related

limitations

  • robustness
  • support

New APIs are coming out all the time. A recent list http://nordicapis.com/20-emotion- recognition-apis-that-will-leave-you-impressed-and-concerned/

  • https://ibug.doc.ic.ac.uk/resources/action-unit-detector-2016/
  • http://affect.media.mit.edu/software.php
  • many, many more

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 31/53

slide-35
SLIDE 35

Measuring Emotions - off-the-shelf solutions

  • Noldus FaceReader
  • Affectiva
  • Amazon Rekognition
  • IBM Tone Analyzer

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 32/53

slide-36
SLIDE 36

Noldus FaceReader

  • standalone software
  • SDKs available in different languages
  • price is relatively high

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 33/53

slide-37
SLIDE 37

Amazon Rekognition

  • Amazon AWS Rekognition DetectFaces API (many SDKs)
  • cloud-based solution
  • detects emotions from single images (not sequence)
  • emotion value (HAPPY | SAD | ANGRY | CONFUSED | DISGUSTED | SURPRISED |

CALM | UNKNOWN)

  • confidence (0-100)
  • AWS costs

https://aws.amazon.com/rekognition/ http://docs.aws.amazon.com/rekognition/latest/dg/API_DetectFaces.html

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 34/53

slide-38
SLIDE 38

Affectiva

  • MIT spin-off
  • cloud-based solution
  • SDKs available in different languages
  • free (we are the data)

DEMO

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 35/53

slide-39
SLIDE 39

IBM Watson Tone Analyzer

  • from text -> JSON file
  • emotions and personality
  • joy, fear, sadness, anger, disgust,
  • analytical, confident, tentative, openness, conscientiousness, extraversion, agreeableness,

and emotional range.

https://tone-analyzer-demo.mybluemix.net/

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 36/53

slide-40
SLIDE 40

Table of Contents

Recap Acquisition of Personality Usage of personality in recommender systems Acquisition of Emotions Usage of emotions in recommender systems Conclusion Hands-on User Study

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 37/53

slide-41
SLIDE 41

Model of usage of emotions in Recommender Systems

References

Tkalčič, M., Košir, A., Tasič, J., and Kunaver, M. (2011). Affective recommender systems: the role of emotions in recommender

  • systems. In A. Felfernig, L. Chen, M. Mandl, M. Willemsen, D. Bollen, and M. Ekstrand (Eds.), Joint proceedings of the RecSys 2011

Workshop on Human Decision Making in Recommender Systems (Decisions@RecSys’11) and User-Centric Evaluation of Recommender Systems and Their Interfaces-2 (UCERSTI 2) affiliated with the 5th ACM Conference on Recommender (pp. 9–13). Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 38/53

slide-42
SLIDE 42

Emotions as context

  • task: recommending music content that fits a place of interest (POI)
  • emotional tags (GEMS) attached by a users’ population to both music and POIs
  • tag-based similarity metrics to match music with POI

References

Marius Kaminskas and Francesco Ricci. 2011. Location-adapted music recommendation using tags. Proceedings of UMAP ’11, Springer-Verlag, Berlin, Heidelberg, 183-194. Kaminskas, M., and Ricci, F. (2016). Emotion-Based Matching of Music to Places (pp. 287–310). In M. Tkalčič, B. De Carolis, M. de Gemmis, A. Odić, and A. Košir (Eds.), Emotions and Personality in Personalized Services: Models, Evaluation and Applications Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 39/53

slide-43
SLIDE 43

Emotions as context

  • CoMoDa dataset
  • various contextualization techniques

References

Yong Zheng, Bamshad Mobasher, Robin D. Burke: The Role of Emotions in Context-aware Recommendation. Decisions@RecSys 2013: 21-28 Zheng, Y., Mobasher, B., and Burke, R. (2016). Emotions in Context-Aware Recommender Systems (pp. 311–326). In M. Tkalčič, B. De Carolis, M. de Gemmis, A. Odić, and A. Košir (Eds.), Emotions and Personality in Personalized Services: Models, Evaluation and Applications Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 40/53

slide-44
SLIDE 44

Affective User Modeling

  • Multimedia content ELICITS (induces) emotions
  • Underlying assumption: users differ in their preferences for emotions

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 41/53

slide-45
SLIDE 45

Affective User Modeling

References

Tkalčič, M., Burnik, U., and 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 Tkalčič, M., Odić, A., Košir, A., and Tasič, J. (2013). Affective labeling in a content-based recommender system for images. IEEE Transactions on Multimedia, 15(2), 391–400. https://doi.org/10.1109/TMM.2012.2229970 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 42/53

slide-46
SLIDE 46

Emotions as feedback

  • video-on-demand scenario
  • usage of hesitation as feedback
  • 4 recommendations, 1 selection
  • control group: recommend similar
  • hesitation group: recommend similar/diverse
  • quality of experience (QoE) is improved when hesitation is taken into account

References

Vodlan, T., Tkalčič, M., and Košir, A. (2015). 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 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 43/53

slide-47
SLIDE 47

Emotions as implicit feedback for assessing serendipity of recommendations

  • Recommending video clips
  • FaceReader (40 MSc students, 26 male)
  • RQ: Is the emotional response of the user useful for assessing serendipity?

Serendipity was measured with

  • questionnaire
  • emotion-based heuristics

A recommended video was deemed serendipitous if

  • duration of positive emotions is longer than

duration of negative emotions

  • after removing neutral

References

Gemmis, M. De, Lops, P., Semeraro, G., and Musto, C. (2015). An investigation on the serendipity problem in recommender systems. Information Processing and Management, 51(5), 695–717. Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 44/53

slide-48
SLIDE 48

Emotional contagion

  • RQ: does emotional contagion occur outside of in-person interactions?
  • Facebook users (N = 689,003)
  • 2 experiments:
  • exposure to friends’ positive emotional content was reduced
  • group (only emotional content omitted)
  • control group (any content omitted)
  • exposure to friends’ negative emotional content was reduced
  • group (only emotional content omitted)
  • control group (any content omitted)

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 45/53

slide-49
SLIDE 49

Existing datasets

  • affective computing . . . but missing interactions
  • content -> emotions
  • stimuli only (IAPS)
  • Small scale
  • LDOS PerAff-1
  • LDOS CoMoDa
  • Large Scale
  • myPersonality http://mypersonality.org/wiki/doku.php

References

Odić, A., Košir, A., and Tkalčič, M. (2016). Affective and Personality Corpora. In M. Tkalcic, B. De Carolis, M. de Gemmis, A. Odic, and A. Košir (Eds.), Emotions and Personality in Personalized Services (pp. 163–178). Springer. Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 46/53

slide-50
SLIDE 50

Table of Contents

Recap Acquisition of Personality Usage of personality in recommender systems Acquisition of Emotions Usage of emotions in recommender systems Conclusion Hands-on User Study

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 47/53

slide-51
SLIDE 51

Conclusion

  • emotions and personality account for differences in user behavior
  • research is still scattered

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 48/53

slide-52
SLIDE 52

Open Issues

  • lack of awareness
  • this tutorial will hopefully help
  • lack of data
  • mostly small-scale data gathered through user studies
  • exceptions:
  • Movielens
  • myPersonality
  • unobtrusive annotation of content
  • subtitles?
  • privacy

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 49/53

slide-53
SLIDE 53

Discussion

Do you have any Answers?

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 50/53

slide-54
SLIDE 54

Table of Contents

Recap Acquisition of Personality Usage of personality in recommender systems Acquisition of Emotions Usage of emotions in recommender systems Conclusion Hands-on User Study

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 51/53

slide-55
SLIDE 55

Table of Contents

Recap Acquisition of Personality Usage of personality in recommender systems Acquisition of Emotions Usage of emotions in recommender systems Conclusion Hands-on User Study

Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 52/53

slide-56
SLIDE 56

Pairwise music scores - user study

Dear SummerSchool participant, Please, take part in our user study at the link below. It should take cca 10 mins of your time. You are warmly welcome to visit us at the RecSys Demo booth next week in Como. Thank you :-) https://recsys.musiclab.si/PairwiseDemo/ References

Marko Tkalčič, Nima Maleki, Matevž Pesek, Mehdi Elahi, Francesco Ricci, Matija Marolt. A Research Tool for User Preferences Elicitation with Facial Expressions. In RecSys 2017, Pages: 353-354 doi:10.1145/3109859.3109978 Marko Tkalčič, RecSys2017SummerSchool-Part2-AcquisitionUsage 53/53