A recommender system for multimedia art collections

In this paper we present a novel user-centered recommendation approach for multimedia art collections. In particular, preferences (usually coded in the shape of items’ metadata), opinions (textual comments to which it is possible to associate a particular sentiment), behavior (in the majority of cases logs of past items’ observations and actions made by users in the environment), and feedbacks (usually expressed in the form of ratings) are considered and integrated together with items’ features and context information within a general and unique recommendation framework that can support an intelligent browsing of any multimedia repository. Preliminary experiments show the utility of the proposed strategy to perform different browsing tasks