From Content Text Encoding Perspective: A Hybrid Deep Matrix Factorization Approach for Recommender System

Abstract

Recommender systems usually make personalized recommendation for users by analyzing interaction ratings between users and items. In plenty of application domains, some implicit feedback, content text, and other additional auxiliary information are widely used for improving the performance of recommendation. Memory-based collaborative filtering approaches that are widely used like matrix factorization (MF) predicts a personalized ranking for an individual user by leveraging latent factor models to handle common problems in recommender systems. However, most of previous MF methods adopt only explicit ratings to make personalized recommendation, ignoring the importance of implicit feedback on both users and items in-formation. Latent factor model can be easily extended with content text by mapping text information into factors, therefore we propose an approach by using neural networks to acquire the latent factors. Meanwhile, recurrent neural networks (RNNs) are applied to convert the textual data to an auxiliary factor feature to promote the representation of items. The experimental results prove that our model is effective on two benchmark datasets, outperforming some state-of-art approaches.