Aspect Based Sentiment Analysis with Aspect-Specific Opinion Spans

TL;DR

This paper introduces a structured attention model using multiple linear-chain CRFs to effectively extract aspect-specific opinion spans for improved sentiment analysis.

Contribution

It presents a novel structured attention approach that captures variable-length opinion spans, enhancing aspect-based sentiment analysis accuracy.

Findings

Effective extraction of aspect-specific opinion spans

Improved sentiment classification performance

Model captures variable-length opinion spans

Abstract

Aspect based sentiment analysis, predicting sentiment polarity of given aspects, has drawn extensive attention. Previous attention-based models emphasize using aspect semantics to help extract opinion features for classification. However, these works are either not able to capture opinion spans as a whole, or not able to capture variable-length opinion spans. In this paper, we present a neat and effective structured attention model by aggregating multiple linear-chain CRFs. Such a design allows the model to extract aspect-specific opinion spans and then evaluate sentiment polarity by exploiting the extracted opinion features. The experimental results on four datasets demonstrate the effectiveness of the proposed model, and our analysis demonstrates that our model can capture aspect-specific opinion spans.