A Content-based Movie Recommender System based on Temporal User Preferences

Recommender systems have emerged as the essential part of many e-commerce web sites. These systems provide personalized services to assist users in finding favorite items among the huge number of available media on the World Wide Web. Identifying temporal preferences of individuals is one of the major challenges of recommender systems to provide personalization for users. In this paper, a content-based movie recommender system is proposed that captures the temporal user preferences in user modeling and predicts the preferred movies. The proposed method provides a user-centered framework that incorporates the content attributes of rated movies (for each user) into a Dirichlet Process Mixture Model to infer user preferences and provide a proper recommendation list. We implement the proposed method and use the MovieLens dataset to perform experiments. The evaluation results show that the performance of proposed recommendation method outperforms the existing movie recommender systems.