Web Items Recommendation Based on Multi-View Clustering

Hong Yu, Tiantian Zhang, JiaXin Chen, Chen Guo, Yahong Lian

Abstract: Nowadays, using recommendation system to provide users with personalized recommendation service is significantly meaningful. However, traditional collaborative filtering methods may suffer from the cold start problem, while another common recommendation model called content-based recommendation may not have the ability to dig out the potential semantic features of web items sufficiently. In this paper, we propose a novel multi-content clustering collaborative filtering model (MCCCF) for recommendation system. The proposed model can apply multi-view clustering to the mining of the similarity and relevance of web items so that they can be used to improve the classic collaborative filtering. Consequently, the data sparsity problem can be solved. We propose to use multi-view clustering to analyse web items or users from different views such as user ratings and user comments so that it discovers deeper similarity and relevance. At the same time, features from multiple views can be used to complement the user views or item views where the features are deficient, which declines the problem of data sparsity drastically. In this way, we can analyse users' preference by their historical interaction features and supplementary behaviour features to give corresponding recommendation. Above all, the weak spots of the traditional model can be filled in and its performance can be improved. Extensive experiments on real world datasets show that our method outperforms the baselines remarkably.