A Semantic Content-based Recommender System Integrating Folksonomies for Personalized Access

Basic content personalization consists in matching up the attributes of a user profile, in which preferences and interests are stored, against the attributes of a content object. The Web 2.0 (r)evolution and the advent of user generated content (UGC) have changed the game for personalization, since the role of people has evolved from passive consumers of information to that of active contributors. One of the forms of UGC that has drawn more attention from the research community is folksonomy, a taxonomy generated by users who collaboratively annotate and categorize resources of interests with freely chosen keywords called tags. In this chapter, we intend to investigate whether folksonomies might be a valuable source of information about user interests for a recommender system. In order to achieve that goal, folksonomies have been included into ITR (ITem Recommender), a content-based recommender system developed at the University of Bari [7]. Specifically, static content consisting of the descriptions of the items in a collection have been enriched with dynamic UGC through social tagging techniques. The new recommender system, called FIRSt (Folksonomy-based Item Recommender syStem), extends the original ITR system integrating UGC management by letting users to express their preferences for items by entering a numerical rating as well as to annotate rated items with free tags. The main contribution of the chapter is an integrated strategy that enables a content-based recommender to infer user interests by applying machine learning techniques, both on official item descriptions provided by a publisher and on tags which users adopt to freely annotate relevant items. Static content and tags are preventively analyzed by advanced linguistic techniques in order to capture the semantics of the user interests, often hidden behind keywords. The proposed approach has been evaluated in the domain of cultural heritage personalization. Experiments involving 40 real users show an improvement in the predictive accuracy of the tag-augmented recommender compared to the pure content-based one.