Learning Distributed Representations from Reviews for Collaborative Filtering

TL;DR

This paper explores neural network models for incorporating review text into collaborative filtering, demonstrating that a product-of-experts model achieves state-of-the-art results, while a recurrent neural network offers less regularization benefit.

Contribution

Introduces neural network-based review models for collaborative filtering, outperforming LDA-based methods and analyzing their effects on recommendation performance.

Findings

Product-of-experts model achieves state-of-the-art performance.

Recurrent neural network model underperforms in regularization.

Neural models offer increased flexibility over LDA.

Abstract

Recent work has shown that collaborative filter-based recommender systems can be improved by incorporating side information, such as natural language reviews, as a way of regularizing the derived product representations. Motivated by the success of this approach, we introduce two different models of reviews and study their effect on collaborative filtering performance. While the previous state-of-the-art approach is based on a latent Dirichlet allocation (LDA) model of reviews, the models we explore are neural network based: a bag-of-words product-of-experts model and a recurrent neural network. We demonstrate that the increased flexibility offered by the product-of-experts model allowed it to achieve state-of-the-art performance on the Amazon review dataset, outperforming the LDA-based approach. However, interestingly, the greater modeling power offered by the recurrent neural network appears to undermine the model's ability to act as a regularizer of the product representations.