Neural Review Rating Prediction with Hierarchical Attentions and Latent Factors

TL;DR

This paper introduces a hierarchical attention model guided by latent factors for improved rating prediction from reviews, emphasizing important reviews and words to enhance recommendation accuracy.

Contribution

It presents a novel hierarchical attention mechanism combined with latent factors to better utilize review information for rating prediction.

Findings

Improved rating prediction accuracy on real-world datasets.

Effective focus on important reviews and words through hierarchical attention.

Enhanced personalization by integrating latent factors.

Abstract

Text reviews can provide rich useful semantic information for modeling users and items, which can benefit rating prediction in recommendation. Different words and reviews may have different informativeness for users or items. Besides, different users and items should be personalized. Most existing works regard all reviews equally or utilize a general attention mechanism. In this paper, we propose a hierarchical attention model fusing latent factor model for rating prediction with reviews, which can focus on important words and informative reviews. Specially, we use the factor vectors of Latent Factor Model to guide the attention network and combine the factor vectors with feature representation learned from reviews to predict the final ratings. Experiments on real-world datasets validate the effectiveness of our approach.