ABSTRACT
Behaviorism is the currently-dominant paradigm for building and evaluating recommender systems. Both the operation and the evaluation of recommender system applications are most often driven by analyzing the behavior of users. In this paper, we argue that listening to what users say about the items and recommendations they like, the control they wish to exert on the output, and the ways in which they perceive the system and not just observing what they do will enable important developments in the future of recommender systems. We provide both philosophical and pragmatic motivations for this idea, describe the various points in the recommendation and evaluation processes where explicit user input may be considered, and discuss benefits that may result from considered incorporation of user preferences at each of these points. In particular, we envision recommender applications that aim to support users' better selves: helping them live the life that they desire to lead. For example, recommender-assisted behavior change requires algorithms to predict not what users choose or do now, inferable from behavioral data, but what they should choose or do in the future to become healthier, fitter, more sustainable, or culturally aware. We hope that our work will spur useful discussion and many new ideas for recommenders that empower their users.
Supplemental Material
- Amatriain, X. 2016. Past, Present, and Future of Recom-mender Systems: An Industry Perspective.Google Scholar
- Anand, S.S. and Mobasher, B. 2007. Contextual Recommendation. From Web to Social Web: Discovering and Deploying User and Content Profiles. B. Berendt, A. Hotho, D. Mladenic, and G. Semeraro, eds. Springer Berlin Heidelberg. 142--160. Google ScholarDigital Library
- Cialdini, R.B. 2001. Influence: Science and Practice. Allyn and Bacon.Google Scholar
- Ekstrand, M.D., Harper, F.M., Willemsen, M.C. and Konstan, J.A. 2014. User Perception of Differences in Recommender Algorithms. Proc. ACM RecSys '14, 161--168. Google ScholarDigital Library
- Ekstrand, M.D., Kluver, D., Harper, F.M. and Konstan, J.A. 2015. Letting Users Choose Recommender Algorithms: An Experimental Study. Proc. ACM RecSys '15, 11--18. Google ScholarDigital Library
- Evans, J. 2014. Twitter's Huge Mistake. TechCrunch.Google Scholar
- Franklin, U.M. 2004. The Real World of Technology. House of Anansi Press.Google Scholar
- Harper, F.M., Xu, F., Kaur, H., Condiff, K., Chang, S. and Terveen, L. 2015. Putting Users in Control of Their Recommendations. Proc. ACM RecSys '15, 3--10. Google ScholarDigital Library
- Hill, W., Stead, L., Rosenstein, M. and Furnas, G. 1995. Recommending and evaluating choices in a virtual community of use. Proc. CHI '95, 194--201. Google ScholarDigital Library
- Kapoor, K., Kumar, V., Terveen, L., Konstan, J.A. and Schrater, P. 2015. "I Like to Explore Sometimes": Adapting to Dynamic User Novelty Preferences. Proc. ACM RecSys '15, 19--26. Google ScholarDigital Library
- Kaptein, M., Markopoulos, P., de Ruyter, B. and Aarts, E. 2015. Personalizing persuasive technologies: Explicit and implicit personalization using persuasion profiles. International Journal of Human-Computer Studies. 77, (May 2015), 38--51. Google ScholarDigital Library
- Knijnenburg, B., Willemsen, M., Gantner, Z., Soncu, H. and Newell, C. 2012. Explaining the user experience of recommender systems. User Modeling and User-Adapted Interaction. 22, 4-5 (Oct. 2012), 441--504. Google ScholarDigital Library
- McNee, S., Kapoor, N. and Konstan, J.A. 2006. Don't Look Stupid: Avoiding Pitfalls When Recommending Research Papers. Proc. ACM CSCW '06, 171. Google ScholarDigital Library
- McNee, S., Riedl, J. and Konstan, J.A. 2006. Making recommendations better: an analytic model for human-recommender interaction. CHI '06 Extended Abstracts (2006), 1103--1108. Google ScholarDigital Library
- Pariser, E. 2011. The Filter Bubble: How the New Personalized Web Is Changing What We Read and How We Think. Penguin. Google ScholarDigital Library
- Phelan, O., McCarthy, K., Bennett, M. and Smyth, B. 2011. Terms of a Feather: Content-Based News Recommendation and Discovery Using Twitter. In Advances in Information Retrieval, LNCS 6611. Springer. 448--459. Google ScholarDigital Library
- Prochaska, J.O. and DiClemente, C.C. 1984. The trans-theoretical approach: crossing traditional boundaries of therapy. Dow Jones-Irwin.Google Scholar
- Prochaska, J.O. and Norcross, J.C. 2001. Stages of change. Psychotherapy: Theory, Research, Practice, Training. 38, 4 (2001), 443--448.Google Scholar
- Rutjes, H., Willemsen, M.C. and IJsselsteijn, W.A. 2016. Understanding Effective Coaching on Healthy Lifestyle by Combining Theory- and Data-Driven Approaches. Proc. Workshop on Personalization in Persuasive Technology at Persuasive 2016.Google Scholar
- Starke, A., Willemsen, M.C. and Snijders, C. 2015. Saving Energy in 1-D: Tailoring Energy-saving Advice Using a Rasch-based Energy Recommender System. Proc. 2nd Int. Workshop on Decision Making and Rec. Sys., 5--8.Google Scholar
- Suchman, L. 1993. Foreword. Participatory Design: Principles and Practices. D. Schuler and A. Namioka, eds. CRC / Lawrence Erlbaum Associates. vii--x.Google Scholar
- Ziegler, C.-N., McNee, S., Konstan, J.A. and Lausen, G. 2005. Improving Recommendation Lists through Topic Diversification. Proc. WWW '05, 22--32. Google ScholarDigital Library
Index Terms
- Behaviorism is Not Enough: Better Recommendations through Listening to Users
Recommendations
Being accurate is not enough: how accuracy metrics have hurt recommender systems
CHI EA '06: CHI '06 Extended Abstracts on Human Factors in Computing SystemsRecommender systems have shown great potential to help users find interesting and relevant items from within a large information space. Most research up to this point has focused on improving the accuracy of recommender systems. We believe that not only ...
Content-based book recommending using learning for text categorization
DL '00: Proceedings of the fifth ACM conference on Digital librariesRecommender systems improve access to relevant products and information by making personalized suggestions based on previous examples of a user's likes and dislikes. Most existing recommender systems use collaborative filtering methods that base ...
Getting to know you: learning new user preferences in recommender systems
IUI '02: Proceedings of the 7th international conference on Intelligent user interfacesRecommender systems have become valuable resources for users seeking intelligent ways to search through the enormous volume of information available to them. One crucial unsolved problem for recommender systems is how best to learn about a new user. In ...
Comments