A Unified Dual-view Model for Review Summarization and Sentiment Classification with Inconsistency Loss

TL;DR

This paper introduces a dual-view model that jointly improves review summarization and sentiment classification by leveraging shared sentiment information and an inconsistency loss to ensure sentiment consistency between review and summary.

Contribution

The paper proposes a novel dual-view model with an inconsistency loss that enhances both review summarization and sentiment classification tasks simultaneously.

Findings

The model outperforms baselines on four real-world datasets.

Inconsistency loss improves sentiment alignment between review and summary.

Joint training benefits both summarization quality and sentiment accuracy.

Abstract

Acquiring accurate summarization and sentiment from user reviews is an essential component of modern e-commerce platforms. Review summarization aims at generating a concise summary that describes the key opinions and sentiment of a review, while sentiment classification aims to predict a sentiment label indicating the sentiment attitude of a review. To effectively leverage the shared sentiment information in both review summarization and sentiment classification tasks, we propose a novel dual-view model that jointly improves the performance of these two tasks. In our model, an encoder first learns a context representation for the review, then a summary decoder generates a review summary word by word. After that, a source-view sentiment classifier uses the encoded context representation to predict a sentiment label for the review, while a summary-view sentiment classifier uses the decoder hidden states to predict a sentiment label for the generated summary. During training, we introduce an inconsistency loss to penalize the disagreement between these two classifiers. It helps the decoder to generate a summary to have a consistent sentiment tendency with the review and also helps the two sentiment classifiers learn from each other. Experiment results on four real-world datasets from different domains demonstrate the effectiveness of our model.