DualCoTs: Dual Chain-of-Thoughts Prompting for Sentiment Lexicon Expansion of Idioms

TL;DR

This paper introduces DualCoTs, a novel method using dual chain-of-thought prompting with large language models to automatically expand sentiment lexicons for idioms in Chinese and English, enhancing sentiment analysis capabilities.

Contribution

It proposes the DualCoTs approach that combines linguistic and psycholinguistic insights for idiom sentiment lexicon expansion using large language models.

Findings

Effective expansion of idiom sentiment lexicons in Chinese and English.

Construction of the EmoIdiomE dataset for idiom sentiment analysis.

Demonstrated improvements over existing methods in idiom sentiment lexicon expansion.

Abstract

Idioms represent a ubiquitous vehicle for conveying sentiments in the realm of everyday discourse, rendering the nuanced analysis of idiom sentiment crucial for a comprehensive understanding of emotional expression within real-world texts. Nevertheless, the existing corpora dedicated to idiom sentiment analysis considerably limit research in text sentiment analysis. In this paper, we propose an innovative approach to automatically expand the sentiment lexicon for idioms, leveraging the capabilities of large language models through the application of Chain-of-Thought prompting. To demonstrate the effectiveness of this approach, we integrate multiple existing resources and construct an emotional idiom lexicon expansion dataset (called EmoIdiomE), which encompasses a comprehensive repository of Chinese and English idioms. Then we designed the Dual Chain-of-Thoughts (DualCoTs) method, which combines insights from linguistics and psycholinguistics, to demonstrate the effectiveness of using large models to automatically expand the sentiment lexicon for idioms. Experiments show that DualCoTs is effective in idioms sentiment lexicon expansion in both Chinese and English. For reproducibility, we will release the data and code upon acceptance.