Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Exploring ChatGPT-based Augmentation Strategies for Contrastive Aspect-based Sentiment Analysis

Lingling Xu, Haoran Xie, S. Joe Qin, Fu Lee Wang, Xiaohui Tao

TL;DR

Three data augmentation strategies based on ChatGPT are explored: context-focused, aspect-focused, and context-aspect data augmentation techniques, with the context-aspect data augmentation strategy performing best and surpassing the performance of the baseline models.

Abstract

Aspect-based sentiment analysis (ABSA) involves identifying sentiment towards specific aspect terms in a sentence and allows us to uncover nuanced perspectives and attitudes on particular aspects of a product, service, or topic. However, the scarcity of labeled data poses a significant challenge to training high-quality models. To address this issue, we explore the potential of data augmentation using ChatGPT, a well-performing large language model (LLM), to enhance the sentiment classification performance towards aspect terms. Specifically, we explore three data augmentation strategies based on ChatGPT: context-focused, aspect-focused, and context-aspect data augmentation techniques. Context-focused data augmentation focuses on changing the word expression of context words in the sentence while keeping aspect terms unchanged. In contrast, aspect-focused data augmentation aims to change aspect terms but keep context words unchanged. Context-Aspect data augmentation integrates the above two data augmentations to generate augmented samples. Furthermore, we incorporate contrastive learning into the ABSA tasks to improve performance. Extensive experiments show that all three data augmentation techniques lead to performance improvements, with the context-aspect data augmentation strategy performing best and surpassing the performance of the baseline models.

Exploring ChatGPT-based Augmentation Strategies for Contrastive Aspect-based Sentiment Analysis

TL;DR

Three data augmentation strategies based on ChatGPT are explored: context-focused, aspect-focused, and context-aspect data augmentation techniques, with the context-aspect data augmentation strategy performing best and surpassing the performance of the baseline models.

Abstract

Aspect-based sentiment analysis (ABSA) involves identifying sentiment towards specific aspect terms in a sentence and allows us to uncover nuanced perspectives and attitudes on particular aspects of a product, service, or topic. However, the scarcity of labeled data poses a significant challenge to training high-quality models. To address this issue, we explore the potential of data augmentation using ChatGPT, a well-performing large language model (LLM), to enhance the sentiment classification performance towards aspect terms. Specifically, we explore three data augmentation strategies based on ChatGPT: context-focused, aspect-focused, and context-aspect data augmentation techniques. Context-focused data augmentation focuses on changing the word expression of context words in the sentence while keeping aspect terms unchanged. In contrast, aspect-focused data augmentation aims to change aspect terms but keep context words unchanged. Context-Aspect data augmentation integrates the above two data augmentations to generate augmented samples. Furthermore, we incorporate contrastive learning into the ABSA tasks to improve performance. Extensive experiments show that all three data augmentation techniques lead to performance improvements, with the context-aspect data augmentation strategy performing best and surpassing the performance of the baseline models.
Paper Structure (16 sections, 4 equations, 3 figures, 6 tables)

This paper contains 16 sections, 4 equations, 3 figures, 6 tables.

Table of Contents

  1. Related Work
  2. Methodology
  3. Task Formulation
  4. Data Augmentation
  5. Context-focused Data Augmentation (CDA)
  6. Aspect-focused Data Augmentation (ADA)
  7. Context-Aspect Data Augmentation (CADA)
  8. Training Objective
  9. Experiments
  10. Dataset
  11. Baselines
  12. Implementation Details
  13. Main Results
  14. Sensitivity Analysis
  15. Conclusion
  16. ...and 1 more sections

Figures (3)

  • Figure 1: The overall framework of our proposed method.
  • Figure 2: Sensitivity analysis of the augmented cross-entropy loss hyper-parameter $\alpha$ in supervised aspect-based sentiment classification under different data augmentation strategies.
  • Figure 3: Sensitivity analysis of the contrastive learning hyper-parameter $\beta$ in total training objective with three data augmentation strategies and data verification.