Evaluating the effectiveness of explanations for recommender systems
- 1.1k Downloads
- 27 Citations
Abstract
When recommender systems present items, these can be accompanied by explanatory information. Such explanations can serve seven aims: effectiveness, satisfaction, transparency, scrutability, trust, persuasiveness, and efficiency. These aims can be incompatible, so any evaluation needs to state which aim is being investigated and use appropriate metrics. This paper focuses particularly on effectiveness (helping users to make good decisions) and its trade-off with satisfaction. It provides an overview of existing work on evaluating effectiveness and the metrics used. It also highlights the limitations of the existing effectiveness metrics, in particular the effects of under- and overestimation and recommendation domain. In addition to this methodological contribution, the paper presents four empirical studies in two domains: movies and cameras. These studies investigate the impact of personalizing simple feature-based explanations on effectiveness and satisfaction. Both approximated and real effectiveness is investigated. Contrary to expectation, personalization was detrimental to effectiveness, though it may improve user satisfaction. The studies also highlighted the importance of considering opt-out rates and the underlying rating distribution when evaluating effectiveness.
Keywords
Recommender systems Metrics Item descriptions Explanations Empirical studiesPreview
Unable to display preview. Download preview PDF.
References
- Ahn, J.W., Brusilovsky, P., Grady, J., He, D., Syn, S.Y.: Open user profiles for adaptive news systems: help or harm? In: Proceedings of the 16th International Conference on World Wide Web, pp. 11–20. Banff, Alberta, Canada (2007)Google Scholar
- Ardissono L., Goy A., Petrone G., Segnan M., Torasso P.: INTRIGUE: personalized recommendation of tourist attractions for desktop and handheld devices. Appl. Artif. Intell. 17, 687–714 (2003)CrossRefGoogle Scholar
- Bilgic, M., Mooney, R.J.: Explaining recommendations: satisfaction vs. promotion. In: Proceedings of the Workshop Beyond Personalization, in Conjunction with the International Conference on Intelligent User Interfaces, pp. 13–18. San Diego, CA (2005)Google Scholar
- Billsus, D., Pazzani, M.J.: A personal news agent that talks, learns, and explains. In: Proceedings of the Third International Conference on Autonomous Agents, pp. 268–275. Seattle, WA (1999)Google Scholar
- Carenini, G., Moore, D.J.: An empirical study of the influence of user tailoring on evaluative argument effectiveness. In: Proceedings of the 17th International Joint Conference on Artificial Intelligence, pp. 1307–1314. Seattle, WA (2001)Google Scholar
- Chen, L., Pu, P.: Hybrid critiquing-based recommender systems. In: International Conference on Intelligent User Interfaces, pp. 22–31. Honolulu, HI, USA (2007)Google Scholar
- Cho Y., Im I., Hiltz J.F.S.R.: The impact of product category on customer dissatisfaction in cyberspace. Bus. Process Manag. J. 9(5), 635–651 (2003)CrossRefGoogle Scholar
- Cramer, H., Evers, V., Someren, M.V., Ramlal, S., Rutledge, L., Stash, N., Aroyo, L., Wielinga, B.: The effects of transparency on perceived and actual competence of a content-based recommender. In: Semantic Web User Interaction Workshop in Conjuction with the International Conference on Human Factors in Computing Systems, pp. 455–496. Florence, Italy (2008a)Google Scholar
- Cramer H.S.M., Evers V., Ramlal S., van Someren M., Rutledge L., Stash N., Aroyo L., Wielinga B.J.: The effects of transparency on trust in and acceptance of a content-based art recommender. User Model. User Adapt. Interact. 18(5), 455–496 (2008b)CrossRefGoogle Scholar
- Czarkowski, M.: A scrutable adaptive hypertext. PhD thesis, University of Sydney (2006)Google Scholar
- Dale, R.: Dynamic document delivery: generating natural language texts on demand. In: Proceedings of the 9th International Workshop on Database and Expert Systems Applications, DEXA ’98, pp. 131–136. IEEE Computer Society, Vienna, Austria (1998)Google Scholar
- Felfernig A., Gula B., Teppan E.: User acceptance of knowledge-based recommenders. Mach. Percept. Artif. Intell. 70, 249–276 (2007)CrossRefGoogle Scholar
- Felfernigm, A., Gula, B., Letiner, G., Maier, M., Melcher, R., Schippel, S., Teppan, E.: A dominance model for the calculation of decoy products in recommendation environments. In: Symposium on Persuasive Technology in Conjuction with Artificial Intelligence and the Simulation of Behavior Convention, pp. 43–50. Aberdeen, Scotland (2008)Google Scholar
- Guy, I., Ronen, I., Wilcox, E.: Do you know? Recommending people to invite into your social network. In: International Conference on Intelligent User Interfaces, pp. 77–86. Sanibel Island, FL, USA (2009a)Google Scholar
- Guy, I., Zwerdling, N., Carmel, D., Ronen, I., Uziel, E., Yogev, S., Ofek-Koifman, S.: Personalized recommendation of social software items based on social relations. In: ACM Conference on Recommender systems, pp. 53–60. New York City, NY, USA (2009b)Google Scholar
- Häubl G., Trifts V.: Consumer decision making in online shopping environments: the effects of interactive decision aids. Market. Sci. 19, 4–21 (2000)CrossRefGoogle Scholar
- Herlocker, J.L., Konstan, J.A., Riedl, J.: Explaining collaborative filtering recommendations. In: ACM Conference on Computer Supported Cooperative Work, pp. 241–250. Philadelphia, PA, USA (2000)Google Scholar
- Hingston, M.: User friendly recommender systems. Master’s thesis, Sydney University, Australia (2006)Google Scholar
- Laband D.N.: An objective measure of search versus experience goods. Econ. Inq. 29(3), 497–509 (1991)CrossRefGoogle Scholar
- Masthoff J.: The evaluation of adaptive systems. In: Patel, N. (eds) Adaptive Evolutionary Information Systems, pp. 329–347. Idea group publishing, Hershey, PA (2002)CrossRefGoogle Scholar
- Masthoff J.: Group modeling: selecting a sequence of television items to suit a group of viewers. User Model. User Adapt. Interact. 14, 37–85 (2004)CrossRefGoogle Scholar
- McCarthy, K., Reilly, J., McGinty, L., Smyth, B.: Thinking positively—explanatory feedback for conversational recommender systems. In: Explanation Workshop in Conjunction with the European Conference on Case-Based Reasoning, pp. 115–124. Madrid, Spain (2004)Google Scholar
- McCarthy, K., Reilly, J., McGinty, L., Smyth, B.: Experiments in dynamic critiquing. In: International Conference on Intelligent User Interfaces, pp. 175–182. San Diego, CA, USA (2005a)Google Scholar
- McCarthy K., Reilly J., Smyth B., Mcginty L.: Generating diverse compound critiques. Artif. Intell. Rev. 24, 339–357 (2005b)CrossRefGoogle Scholar
- McNee, S.M., Riedl, J., Konstan, J.A.: Being accurate is not enough: how accuracy metrics have hurt recommender systems. In: International Conference on Human Factors in Computing Systems, pp. 1097–1101. Montreal, Canada (2006a)Google Scholar
- McNee, S.M., Riedl, J., Konstan, J.A.: Making recommendations better: An analytic model for human-recommender interaction. In: Extended Abstracts of the 2006 ACM Conference on Human Factors in Computing Systems (CHI 2006), pp. 1103–1108. Montreal, Canada (2006b)Google Scholar
- McSherry D.: Explanation in recommender systems. Artif. Intell. Rev. 24(2), 179–197 (2005)MATHCrossRefGoogle Scholar
- Murphy P.E., Enis B.M.: Classifying products strategically. J. Market. 50, 24–42 (1986)CrossRefGoogle Scholar
- Oberlander, J., Mellish, C.: Final report on the ILEX project. online: http://www.hcrc.ed.ac.uk/ilex/final.html (1998)
- Paramythis A., Weibelzahl S., Masthoff J.: Layered evaluation of interactive adaptive systems: framework and formative methods. User Model. User Adapt. Interact. 20, 383–453 (2010)CrossRefGoogle Scholar
- Pommeranz, A., Broekens, J., Wiggers, P., Brinkman, W.P., Jonker, C.M.: Designing interfaces for explicit preference elicitation: a user-centered investigation of preference representation and elicitation process. User Model. User Adapt. Interact. 22 (2012). doi: 10.1007/s11257-011-9116-6
- Pu, P., Chen, L.: Trust building with explanation interfaces. In: International Conference on Intelligent User Interfaces, pp. 93–100. Sydney, Australia (2006)Google Scholar
- Pu P., Chen L.: Trust-inspiring explanation interfaces for recommender systems. Knowl. Syst. 20, 542–556 (2007)MathSciNetCrossRefGoogle Scholar
- Pu, P., Chen, L., Hu, R.: Evaluating recommender systems from the user’s perspective: survey of the state of the art. User Model. User Adapt. Interact. 22 (2012). doi: 10.1007/s11257-011-9115-7
- Rashid, A.M., Albert, I., Cosley, D., Lam, S.K., McNee, S.M., Konstan, J.A., Riedl, J.: Getting to know you: learning new user preferences in recommender systems. In: International Conference on Intelligent User Interfaces, pp. 127–134. San Francisco, CA, USA (2002)Google Scholar
- Reilly, J., McCarthy, K., McGinty, L., Smyth, B.: Incremental critiquing. In: SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, pp. 143–151. Cambridge, UK (2004)Google Scholar
- Ricci, F., Rokach, L., Shapira, B., Kantor, P. (eds): Recommender Systems Handbook. Springer, Dordrecht (2010)Google Scholar
- Roth-Berghofer, T., Schulz, S., Leake, D.B., Bahls, D.: Workshop on explanation-aware computing. In: European Conference on Artificial Intelligence, Patras, Greece (2008)Google Scholar
- Roth-Berghofer, T., Tintarev, N., Leake, D.B.: Workshop on explanation-aware computing. In: International Joint Conference on Artificial Intelligence, Pasadena, CA, USA (2009)Google Scholar
- Roth-Berghofer, T., Tintarev, N., Leake, D.B.: Workshop on explanation-aware computing. In: European Conference on Artificial Intelligence, Lisbon, Portugal (2010)Google Scholar
- Shapiro C.: Optimal pricing of experience goods. Bell J. Econ. 14(2), 497–507 (1983)CrossRefGoogle Scholar
- Sinha, R., Swearingen, K.: The role of transparency in recommender systems. In: Conference on Human Factors in Computing Systems, pp. 830–831. Minneapolis, MN, USA (2002)Google Scholar
- Symeonidis, P., Nanopoulos, A., Manolopoulos, Y.: Justified recommendations based on content and rating data. In: Workshop on Web Mining and Web Usage Analysis in Conjunction with the International Conference on Knowledge Discovery and Data Mining, Las Vegas, NV, USA (2008)Google Scholar
- Thompson C.A., Göker M.H., Langley P.: A personalized system for conversational recommendations. J. Artif. Intell. Res. 21, 393–428 (2004)Google Scholar
- Tintarev, N., Masthoff, J.: Effective explanations of recommendations: user-centered design. In: Recommender Systems, pp. 153–156. Minneapolis, MN, USA (2007a)Google Scholar
- Tintarev, N., Masthoff, J.: A survey of explanations in recommender systems. In: WPRSIUI Associated with ICDE’07, pp. 801–810. Istanbul, Turkey (2007b)Google Scholar
- Tintarev, N., Masthoff, J.: Over- and underestimation in different product domains. In: Workshop on Recommender Systems in Conjunction with the European Conference on Artificial Intelligence, pp. 14–19. Patras, Greece (2008a)Google Scholar
- Tintarev, N., Masthoff, J.: Personalizing movie explanations using commercial meta-data. In: International Conference on Adaptive Hypermedia, pp. 204–213. Hannover, Germany (2008b)Google Scholar
- Tintarev, N., Masthoff, J.: Evaluating recommender explanations: Problems experienced and lessons learned for evaluation of adaptive systems. In: UCDEAS Workshop in Conjuction with UMAP, pp. 54–63, Trento, Italy (2009)Google Scholar
- Tintarev N., Masthoff J.: Designing and evaluating explanations for recommender systems. In: Kantor, P.B., Ricci, F., Rokach, L., Shapira, B. (eds) Recommender Systems Handbook, pp. 479–510. Springer, Dordrecht (2010)Google Scholar
- Vig, J., Sen, S., Riedl, J.: Tagsplanations: Explaining recommendations using tags. In: International Conference on Intelligent User Interfaces, pp. 47–56. Sanibel Island, FL, USA (2009)Google Scholar
- Wang W., Benbasat I.: Recommendation agents for electronic commerce: effects of explanation facilities on trusting beliefs. J. Manag. Inf. Syst. 23, 217–246 (2007)CrossRefGoogle Scholar
- Wärnestål, P.: User evaluation of a conversational recommender system. In: Workshop on Knowledge and Reasoning in Practical Dialogue Systems in Conjunction with the International Joint Conference on Artificial Intelligence, pp. 32–39. Edinburgh, Scotland (2005)Google Scholar