DualCoTs: Dual Chain-of-Thoughts Prompting for Sentiment Lexicon Expansion of Idioms
This addresses a bottleneck in text sentiment analysis for researchers and practitioners by enabling more comprehensive emotional expression understanding in real-world texts, though it is incremental as it builds on existing prompting techniques.
The paper tackles the problem of limited sentiment lexicons for idioms by proposing DualCoTs, a method using large language models with Chain-of-Thought prompting to automatically expand these lexicons, showing effectiveness in both Chinese and English with experimental validation.
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.