User preferences modeling using dirichlet process mixture model for a content-based recommender system

Abstract

Recommender systems have been developed to assist users in retrieving relevant resources. Collaborative and content-based filtering are two basic approaches that are used in recommender systems. The former employs the feedback of users with similar interests, while the latter is based on the feature of the selected resources by each user. Recommender systems can consider users’ behavior to more accurately estimate their preferences via a list of recommendations. However, the existing approaches rarely consider both interests and preferences of the users. Also, the dynamic nature of user behavior poses an additional challenge for recommender systems. In this paper, we consider the interactions of each individual user, and analyze them to propose a user model and capture user’s interests. We construct the user model based on a Bayesian nonparametric framework, called the Dirichlet Process Mixture Model. The proposed model evolves following the dynamic nature of user behavior to adapt both the user interests and preferences. We implemented the proposed model and evaluated it using both the MovieLens dataset, and a real-world dataset that contains news tweets from five news channels (New York Times, BBC, CNN, Reuters and Associated Press). The experimental results and comparisons with several recently developed approaches show the superiority in accuracy of the proposed approach, and its ability to adapt with user behavior over time.