Improving Recommendation Performance in Matrix Factorization with Interest Exploring
Wang Zhou, Jianping Li, Ruyu Wu, Yanan Lu, Yujun Yang · 2018
In this article, to improve the recommendation performance, we propose a novel recommender approach, which tries to learn the interest distribution for each user via Latent Dirichlet Allocation, and then incorporate it into matrix factorization. Empirical experiments over real world datasets indicate that the proposed method could achieve significant improvement in contrast to state-of-the-art approaches.