Dual Memory Network Model for Biased Product Review Classification

TL;DR

This paper introduces a dual memory network model that separately learns user profiles and product reviews for sentiment analysis, leading to improved accuracy over existing unified models.

Contribution

The novel dual memory network model effectively captures user and product information separately, enhancing sentiment classification performance.

Findings

Performance gains of 0.6%, 1.2%, and 0.9% on benchmark datasets.

Statistically significant improvements confirmed by p-values.

Outperforms state-of-the-art unified models.

Abstract

In sentiment analysis (SA) of product reviews, both user and product information are proven to be useful. Current tasks handle user profile and product information in a unified model which may not be able to learn salient features of users and products effectively. In this work, we propose a dual user and product memory network (DUPMN) model to learn user profiles and product reviews using separate memory networks. Then, the two representations are used jointly for sentiment prediction. The use of separate models aims to capture user profiles and product information more effectively. Compared to state-of-the-art unified prediction models, the evaluations on three benchmark datasets, IMDB, Yelp13, and Yelp14, show that our dual learning model gives performance gain of 0.6%, 1.2%, and 0.9%, respectively. The improvements are also deemed very significant measured by p-values.