Making the Best Use of Review Summary for Sentiment Analysis

TL;DR

This paper investigates how to effectively utilize review summaries to improve sentiment analysis, proposing a hierarchical review-centric attention model that leverages both user-written and automatically generated summaries, leading to better performance.

Contribution

The paper introduces a novel review-centric attention architecture that enhances sentiment analysis by exploiting the complementary information in review summaries.

Findings

The sentiment signals of reviews and summaries are complementary.

The proposed model outperforms existing methods with user-written summaries.

The model remains effective with automatically generated summaries.

Abstract

Sentiment analysis provides a useful overview of customer review contents. Many review websites allow a user to enter a summary in addition to a full review. Intuitively, summary information may give additional benefit for review sentiment analysis. In this paper, we conduct a study to exploit methods for better use of summary information. We start by finding out that the sentimental signal distribution of a review and that of its corresponding summary are in fact complementary to each other. We thus explore various architectures to better guide the interactions between the two and propose a hierarchically-refined review-centric attention model. Empirical results show that our review-centric model can make better use of user-written summaries for review sentiment analysis, and is also more effective compared to existing methods when the user summary is replaced with summary generated by an automatic summarization system.