Experimenting Combinations of Content-Based and Collaborative Filtering with a Photo Recommender System

With the ongoing information explosion, it is becoming more and more critical to help users in retrieving items of actual interest. This work describes some experiments carried out in the field of photo recommendation, where a collaborative approach is combined in three different ways with a content-based one, in a scenario composed by few users that are very different among them. The content-based approach is an attempt to improve the performances of the collaborative one, by exploiting the textual descriptions that usually come with photos. Preliminary experiments show that improvements in the precision can be achieved for some users, although - in this particular context - the collaborative approach is on the average preferable.