Dual-Prior Review-Based Matrix Factorization for Recommendation System

Abstract

Many studies utilizing review information to overcome the rating data sparsity obstacle in recommender systems because its abundant information and outstanding explainability. These methods consider reviews as attributes for users and items. They using aggregated review texts from a user and aggregated review texts for an item to model user and item respectively. However, on the one hand, reviews are actually a kind of interactive feature. The item-related features will be incorporated when modeling users by reviews and the same goes for modeling items. On the other hand, it’s a serious challenge for them to build accurate item features because of the reviews are from a lot of users who have different preference. The same goes for building user features with all user’s reviews. So it is more efficient to use review information to model the interaction characteristics between users and items. In this paper, we propose a collaborative filtering (CF) framework, Dual-Prior Review-based Matrix Factorization (DPRMF), a model integrates review information into probabilistic matrix factorization (PMF) model. DPRMF using convolutional neural networks (CNNs) to generate the review text information vector and considering the review information a prior constraint of interaction between user and item. Extensive experiments on benchmark datasets of Amazon and Yelp on different domains show that the proposed DPRMF model consistently outperforms the state-of-the-art review-based recommendation approaches, including PMF, HFT, DeepCoNN and NARRE. In addition, we use word-level vector weights in the embedding layer of our CNN architecture, which help us visualize the reviews and interpretate our model more intuitive.