Cross-representation mediation of user models

Personalization is considered a powerful methodology for improving the effectiveness of information search and decision making. It has led to the dissemination of systems capable of suggesting relevant and personalized information (or items) to the users, according to their characteristics and preferences, as represented by a User Model (UM). Since the quality of the personalization largely depends on the size and accuracy of the managed UMs, it would be beneficial to enrich the UMs by mediating, i.e., importing and integrating, UMs built by other personalization systems. This work discusses and evaluates a cross-representation mediation of UMs from collaborative filtering to content-based recommender systems. According to this approach, a content-based recommender system, having partial or no UM data, can generate recommendations for users by mediating UM data of the same users, collected by a collaborative filtering system. The mediation process transforms the UMs from the collaborative filtering ratings to the content-based weighted item features. The mediation process exploits the item descriptions that are typically not used by the collaborative filtering recommender systems. An experimental evaluation conducted in the domain of movies shows that for users with small collaborative filtering UMs, i.e., users with few item ratings, the accuracy of the recommendations provided using the mediated content-based UMs is superior to that using the original collaborative filtering UMs. Moreover, it shows that the mediation can be used to improve a content-based recommender system by incrementally mediating collaborative filtering UM data (item ratings) and enriching the available content-based UMs.