Rating LDA model for collaborative filtering

摘要: People are pleased with the great wealth of products in online stores. However, it is more and difficult for people to choose their favorite an store. Thus, recommendation systems necessary provide useful suggestions selections. A user's choice not only influenced by his/her interests, but also ratings others. In this paper, we propose a Rating LDA (RLDA) Model collaborative filtering adding rating information Latent Dirichlet Allocation (LDA). User behavior independent; follows trend Therefore, assume that similar higher proportion high ratings, popular items. We perform experiments on two real world data sets: MovieLens100k MovieLens1M. Results show that, terms F1 score, our proposed approach significantly outperforms some baseline methods.