Conversational Case-Based Recommendations Exploiting a Structured Case Model
There are case-based recommender systems that generate personalized recommendations for users exploiting the knowledge contained in past recommendation cases. These systems assume that the quality of a new recommendation depends on the quality of the recorded recommendation cases. In this paper, we present a case model exploited in a mobile critique-based recommender system that generates recommendations using the knowledge contained in previous recommendation cases. The proposed case model is capable of modeling evolving (conversational) recommendation sessions, capturing the recommendation context, supporting critique-based user-system conversations, and integrating both ephemeral and stable user preferences. In this paper, we evaluate the proposed case model through replaying real recommendation cases recorded in a previous live-user evaluation. We measure the impact of the various components of the case model on the system’s recommendation performance. The experimental results show that the case components that model the user’s contextual information, default preferences, and initial preferences, are the most important for mobile context-dependent recommendation.
Unable to display preview. Download preview PDF.
- 1.Aamodt, A., Plaza, E.: Case-based Reasoning: Foundational Issues, Methodological Variations, and System Approaches. AI Communications 7(1), 39–59 (1994)Google Scholar
- 5.Burke, R.: Hybrid Web Recommender Systems. In: Brusilovsky, P., Kobsa, A., Nejdl, W. (eds.) The Adaptive Web: Methods and Strategies of Web Personalization, pp. 377–408. Springer, Heidelberg (2007)Google Scholar
- 6.Chen, L., Pu, P.: Preference-based Organization Interface: Aiding User Critiques in Recommender Systems. In: 11th International Conference on User Modeling, pp. 77–86. Springer, Heidelberg (2007)Google Scholar
- 10.McSherry, D., Aha, D.W.: Mixed-Initiative Relaxation of Constraints in Critiquing Dialogues. In: 7th International Conference on Case-Based Reasoning, pp. 107–121. Springer, Heidelberg (2007)Google Scholar
- 11.Nguyen, Q.N., Ricci, F.: User Preferences Initialization and Integration in Critique-Based Mobile Recommender Systems. In: 5th International Workshop on Artificial Intelligence in Mobile Systems, pp. 71–78. Universitat des Saarlandes Press (2004)Google Scholar
- 14.Ricci, F., Venturini, A., Cavada, D., Mirzadeh, N., Blaas, D., Nones, M.: Product Recommendation with Interactive Query Management and Twofold Similarity. In: 5th International Conference on Case-Based Reasoning, pp. 479–493. Springer, Heidelberg (2003)Google Scholar