A Soft Contrastive Learning-based Prompt Model for Few-shot Sentiment Analysis

TL;DR

This paper introduces a novel soft contrastive learning-based prompt model for few-shot sentiment analysis, effectively capturing subtle semantic differences among sentiment classes through a sentiment-aware reasoning prompt and a correlation-aware contrastive learning approach.

Contribution

The paper presents a new prompt model combining sentiment-aware reasoning prompts with soft contrastive learning to improve few-shot sentiment classification accuracy.

Findings

Outperforms state-of-the-art baselines including ChatGPT.

Effective in distinguishing subtle sentiment class differences.

Demonstrates robustness across multiple sentiment datasets.

Abstract

Few-shot text classification has attracted great interest in both academia and industry due to the lack of labeled data in many fields. Different from general text classification (e.g., topic classification), few-shot sentiment classification is more challenging because the semantic distances among the classes are more subtle. For instance, the semantic distances between the sentiment labels in a positive or negative polarity (e.g., ``love" and ``joy", ``remorse" and ``sadness") are close, while the distances are large for the sentiment labels in two opposite polarities (e.g., ``love" and ``sadness"). To address this problem, we propose a Soft Contrastive learning-based Prompt (\texttt{SCP}) model for few-shot sentiment analysis. First, we design a sentiment-aware chain of thought prompt module to guide the model to predict the sentiment from coarse grain to fine grain via a series of intermediate reasoning steps. Then, we propose a soft contrastive learning algorithm to take the correlation of the labels into account. A series of experiments on several sentiment analysis datasets show the great advantages of \texttt{SCP} by comparing it with SOTA baselines (e.g., ChatGPT).