A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis

TL;DR

This paper introduces a new counterfactual data augmentation technique for aspect-based sentiment analysis that reverses opinion expressions to improve model robustness and performance across multiple datasets.

Contribution

It presents a simple, effective method using integrated gradients and PLMs to generate reversed sentiment expressions for data augmentation in ABSA.

Findings

Outperforms existing augmentation methods on three datasets

Improves model accuracy and robustness in ABSA tasks

Effective across diverse domains like laptops and restaurants

Abstract

Aspect-based-sentiment-analysis (ABSA) is a fine-grained sentiment evaluation task, which analyzes the emotional polarity of the evaluation aspects. Generally, the emotional polarity of an aspect exists in the corresponding opinion expression, whose diversity has great impact on model's performance. To mitigate this problem, we propose a novel and simple counterfactual data augmentation method to generate opinion expressions with reversed sentiment polarity. In particular, the integrated gradients are calculated to locate and mask the opinion expression. Then, a prompt combined with the reverse expression polarity is added to the original text, and a Pre-trained language model (PLM), T5, is finally was employed to predict the masks. The experimental results shows the proposed counterfactual data augmentation method performs better than current augmentation methods on three ABSA datasets, i.e. Laptop, Restaurant, and MAMS.