ABSTRACT
Recommender systems have become pervasive on the web, shaping the way users see information and thus the decisions they make. As these systems get more complex, there is a growing need for transparency. In this paper, we study the problem of generating and visualizing personalized explanations for hybrid recommender systems, which incorporate many different data sources. We build upon a hybrid probabilistic graphical model and develop an approach to generate real-time recommendations along with personalized explanations. To study the benefits of explanations for hybrid recommender systems, we conduct a crowd-sourced user study where our system generates personalized recommendations and explanations for real users of the last.fm music platform. We experiment with 1) different explanation styles (e.g., user-based, item-based), 2) manipulating the number of explanation styles presented, and 3) manipulating the presentation format (e.g., textual vs. visual). We apply a mixed model statistical analysis to consider user personality traits as a control variable and demonstrate the usefulness of our approach in creating personalized hybrid explanations with different style, number, and format.
Supplemental Material
- G. Adomavicius, N. Manouselis, and Y. Kwon. 2015. Multi-Criteria Recommender Systems. Recommender Systems Handbook, Second Edition, Springer US. Google ScholarDigital Library
- I. Andjelkovic, D. Parra, and J. O'Donovan. 2019. Moodplay: interactive music recommendation based on artists' mood similarity. International Journal of Human-Computer Studies, 121.Google Scholar
- S. Bach, M. Broecheler, B. Huang, and L. Getoor. 2017. Hinge-loss markov random fields and probabilistic soft logic. Journal of Machine Learning Research. (JMLR'17) 18, 109. Google ScholarDigital Library
- Y. Benjamini and Y. Hochberg. 1995. Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal Statistical Society. (JRSS '95) 18, 109.Google Scholar
- S. Berkovsky, R. Taib, and D. Conway. 2017. How to recommend?: user trust factors in movie recommender systems. In Proceedings of the 22nd International Conference on Intelligent User Interfaces (IUI '17). Google ScholarDigital Library
- M. Bilgic and R. Mooney. 2005. Explaining recommendations: satisfaction vs. promotion. In Beyond Personalization Workshop in conjunction with International Conference on Intelligent User Interfaces (IUI '05).Google Scholar
- S. Bostandjiev, J. O'Donovan, and T. Höllerer. 2012. Tasteweights: a visual interactive hybrid recommender system. In Proceedings of the 6th ACM Conference on Recommender Systems (RecSys '12). Google ScholarDigital Library
- D. Campbell and D. Fiske. 1959. Convergent and discriminant validation by the multitrait-multimethod matrix. Psychological Bulletin, 56, 2.Google ScholarCross Ref
- S. Chang, F. Harper, and L. Terveen. 2016. Crowd-based personalized natural language explanations for recommendations. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys '16). Google ScholarDigital Library
- R. Cribbie. 2007. Multiplicity control in structural equation modeling. Structural Equation Modeling, 14, 1.Google ScholarCross Ref
- G. Friedrich and M. Zanker. 2017. A taxonomy for generating explanations in recommender systems. AI Magazine, 32, 3.Google Scholar
- Z. Gantner, S. Rendle, C. Freudenthaler, and L. Schmidt-Thieme. 2011. My-medialite: a free recommender system library. In Proceedings of the 5th ACM Conference on Recommender Systems (RecSys '11). Google ScholarDigital Library
- F. Gedikli, D. Jannach, and M. Ge. 2014. How should i explain? a comparison of different explanation types for recommender systems. International Journal of Human-Computer Studies, 72, 4. Google ScholarDigital Library
- S. Gosling, P. Rentfrow, and W. Swann. 2003. A very brief measure of the big-five personality domains. Journal of Research in Personality, 37, 6.Google ScholarCross Ref
- J. Herlocker, J. Konstan, and J. Riedl. 2000. Explaining collaborative filtering recommendations. In Proceedings of the Conference on Computer Supported Cooperative Work (CSCW '00). Google ScholarDigital Library
- J. Herlocker, J. Konstan, L. Terveen, and J. Riedl. 2004. Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems. (TOIS '04) 22, 1. Google ScholarDigital Library
- Y. Hu, Y. Koren, and C. Volinsky. 2008. Collaborative filtering for implicit feedback datasets. In IEEE International Conference on Data Mining (ICDM '08). Google ScholarDigital Library
- P. Ipeirotis. 2010. Mechanical turk: now with 40.92% spam. http://www.behind-the-enemy-lines.com/2010/12/mechanical-turk-now-with-4092-spam.html.Blog. (2010).Google Scholar
- D. Jannach, I. Kamehkhosh, and L. Lerche. 2017. Leveraging multi-dimensional user models for personalized next-track music recommendation. In Proceedings of the Symposium on Applied Computing (SAC '17). Google ScholarDigital Library
- B. Knijnenburg, S. Bostandjiev, J. O'Donovan, and A. Kobsa. 2012. Inspectability and control in social recommenders. In Proceedings of the 6th ACM Conference on Recommender Systems (RecSys '12). Google ScholarDigital Library
- P. Kouki, S. Fakhraei, J. Foulds, M. Eirinaki, and L. Getoor. 2015. Hyper: a flexible and extensible probabilistic framework for hybrid recommender systems. In Proceedings of the 9th ACM Conference on Recommender Systems (RecSys '15). Google ScholarDigital Library
- P. Kouki, J. Schaffer, J. Pujara, J. O'Donovan, and L. Getoor. 2017. User preferences for hybrid explanations. In Proceedings of the 11th ACM Conference on Recommender Systems (RecSys '17). Google ScholarDigital Library
- T. Nguyen, D. Kluver, T. Wang, P. Hui, M. Ekstrand, M. Willemsen, and J. Riedl. 2013. Rating support interfaces to improve user experience and recommender accuracy. In Proceedings of the 7th ACM Conference on Recommender Systems (RecSys '13). Google ScholarDigital Library
- X. Ning, C. Desrosiers, and G. Karypis. 2015. A comprehensive survey of neighborhood based recommendation methods. Recommender Systems Handbook, Second Edition, Springer US. Google ScholarDigital Library
- I. Nunes and D. Jannach. 2017. A systematic review and taxonomy of explanations in decision support and recommender systems. User Modeling and User-Adapted Interaction. (UMUAI'17) 27, 3--5. Google ScholarDigital Library
- J. O'Donovan, B. Smyth, B. Gretarsson, S. Bostandjiev, and T. Höllerer. 2008. Peerchooser: visual interactive recommendation. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '08). Google ScholarDigital Library
- S. Oramas, L. Espinosa-Anke, M. Sordo, H. Saggion, and X. Serra. 2016. Information extraction for knowledge base construction in the music domain. Data & Knowledge Engineering, 106, C. Google ScholarDigital Library
- A. Papadimitriou, P. Symeonidis, and Y. Manolopoulos. 2012. A generalized taxonomy of explanations styles for traditional and social recommender systems. Data Mining and Knowledge Discovery, 24, 3. Google ScholarDigital Library
- D. Parra, P. Brusilovsky, and C. Trattner. 2014. See what you want to see: visual user-driven approach for hybrid recommendation. In Proceedings of the 19th International Conference on Intelligent User Interfaces (IUI '14). Google ScholarDigital Library
- S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme. 2009. BPR: bayesian personalized ranking from implicit feedback. In Proceedings of the 25th Conference on Uncertainty under Artificial Intelligence (UAI '09). Google ScholarDigital Library
- M. Sato, B. Ahsan, K. Nagatani, T. Sonoda, Q. Zhang, and T. Ohkuma. 2018. Explaining recommendations using contexts. In Proceedings of the 23rd International Conference on Intelligent User Interfaces (IUI '18). Google ScholarDigital Library
- J. Schaffer, J. O'Donovan, and T. Höllerer. 2018. Easy to please: separating user experience from choice satisfaction. In Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization (UMAP'18). Google ScholarDigital Library
- P. Symeonidis, A. Nanopoulos, and Y. Manolopoulos. 2009. Moviexplain: a recommender system with explanations. In Proceedings of the 3rd ACM Conference on Recommender Systems (RecSys '09). Google ScholarDigital Library
- M. Tavakol and R. Dennick. 2011. Making sense of cronbach's alpha. International Journal of Medical Education, 2.Google Scholar
- N. Tintarev and J. Masthoff. 2012. Evaluating the effectiveness of explanations for recommender systems. User Modeling and User-Adapted Interaction. (UMUAI'12) 22, 4--5. Google ScholarDigital Library
- M. Tkalcic and L. Chen. 2015. Personality and Recommender Systems. Recommender Systems Handbook, Second Edition, Springer US. Google ScholarDigital Library
- J. Tukey. 1949. Comparing individual means in the analysis of variance. Biometrics.Google Scholar
- J. Ullman and P. Bentler. 2003. Structural equation modeling. Wiley Online Library.Google Scholar
- K. Verbert, D. Parra, P. Brusilovsky, and E. Duval. 2013. Visualizing recommendations to support exploration, transparency and controllability. In Proceedings of the 18th International Conference on Intelligent User Interfaces (IUI '13). Google ScholarDigital Library
- J. Vig, S. Sen, and J. Riedl. 2009. Tagsplanations: explaining recommendations using tags. In Proceedings of the 14th International Conference on Intelligent User Interfaces (IUI '09). Google ScholarDigital Library
Index Terms
- Personalized explanations for hybrid recommender systems
Recommendations
Generating and Understanding Personalized Explanations in Hybrid Recommender Systems
Special Issue on IUI 2019 HighlightsRecommender systems are ubiquitous and shape the way users access information and make decisions. As these systems become more complex, there is a growing need for transparency and interpretability. In this article, we study the problem of generating ...
The Adaptive Ontology-Based Personalized Recommender System
Recommender systems provide strategies that help users search or make decisions within the overwhelming information spaces nowadays. They have played an important role in various areas such as e-commerce and e-learning. In this paper, we propose a ...
Dynamic generation of personalized hybrid recommender systems
RecSys '13: Proceedings of the 7th ACM conference on Recommender systemsThe problem of information overload has been a relevant and active research topic for the past twenty years. Since then, numerous algorithms and recommendation approaches have been proposed, which gives rise to a new type of problem: recommendation ...
Comments