Acquiring Common Chinese Emotional Events Using Large Language Model

TL;DR

This paper presents a method to automatically generate and classify a large-scale Chinese emotional events knowledge base using a large language model, enhancing emotion understanding in Chinese NLP applications.

Contribution

It introduces a novel approach combining LLM prompting and filtering to create the first extensive Chinese emotional events knowledge base with sentiment labels.

Findings

Successfully generated 102,218 emotional events with sentiment polarity.

Demonstrated effectiveness in emotion cause extraction tasks.

Provided resources for future Chinese emotion research.

Abstract

Knowledge about emotional events is an important kind of knowledge which has been applied to improve the effectiveness of different applications. However, emotional events cannot be easily acquired, especially common or generalized emotional events that are context-independent. The goal of this paper is to obtain common emotional events in Chinese language such as "win a prize" and "be criticized". Our approach begins by collecting a comprehensive list of Chinese emotional event indicators. Then, we generate emotional events by prompting a Chinese large language model (LLM) using these indicators. To ensure the quality of these emotional events, we train a filter to discard invalid generated results. We also classify these emotional events as being positive events and negative events using different techniques. Finally, we harvest a total of 102,218 high-quality common emotional events with sentiment polarity labels, which is the only large-scale commonsense knowledge base of emotional events in Chinese language. Intrinsic evaluation results show that the proposed method in this paper can be effectively used to acquire common Chinese emotional events. An extrinsic use case also demonstrates the strong potential of common emotional events in the field of emotion cause extraction (ECE). Related resources including emotional event indicators and emotional events will be released after the publication of this paper.