Mixed Collaborative and Content-Based Filtering with User-Contributed Semantic Features

Abstract

We describe a recommender system which uses a unique combination of content-based and collaborative methods to suggest items of interest to users, and also to learn and exploit item semantics. Recommender systems typically use tech-niques from collaborative filtering, in which proximity mea-sures between users are formulated to generate recommenda-tions, or content-based filtering, in which users are compared directly to items. Our approach uses similarity measures be-tween users, but also directly measures the attributes of items that make them appealing to specific users. This can be used to directly make recommendations to users, but equally im-portantly it allows these recommendations to be justified. We introduce a method for predicting the preference of a user for a movie by estimating the user’s attitude toward features with which other users have described that movie. We show that this method allows for accurate recommenda-tions for a sub-population of users, but not for the entire user population. We describe a hybrid approach in which a user-specific recommendation mechanism is learned and experi-mentally evaluated. It appears that such a recommender sys-tem can achieve significant improvements in accuracy over alternative methods, while also retaining other advantages.