Case-Based Aggregation of Preferences for Group Recommenders

Abstract

Abstract. We extend a group recommender system with a case base of previous group recommendation events. We show that this offers a new way of aggregating the predicted ratings of the group members. Using user-user similarity, we align individuals from the active group with individuals from the groups in the cases. Then, using item-item similarity, we transfer the preferences of the groups in the cases over to the group that is seeking a recommendation. The advantage of a case-based approach to preference aggregation is that it does not require us to commit to a model of social behaviour, expressed in a set of formulae, that may not be valid across all groups. Rather, the CBR system's aggregation of the predicted ratings will be a lazy and local generalization of the behaviours captured by the neighbouring cases in the case base.

How Case-Based Reasoning on e-Community Knowledge Can Be Improved Thanks to Knowledge Reliability

“…Meta-knowledge is already used in CBR, mainly for case base maintenance and recommendation. [10] presents a CBR system recommending movies to a group according to movies watched, in the past, by other groups. The similarity between two groups depends on the similarity between their members, one by one, and takes into account the degree of trust in addition to other criteria (age, gender, etc.).…”

Sentiment and Preference Guided Social Recommendation

“…The huge success of these systems in the retail sector is also its main driving force towards innovative and improved recommendation algorithms. Representation, similarity and ranking algorithms from the Case-Based Reasoning (CBR) community has naturally made a significant contribution to recommender systems research [18,23]. The dawn of the social web creates many new opportunities for recommendation algorithms and so the emergence of social recommender systems [9,12].…”