Implicit Sentiment Analysis Based on Chain of Thought Prompting

TL;DR

This paper introduces a novel implicit sentiment analysis framework leveraging large language model Chain of Thought prompting, demonstrating significant performance improvements on benchmark datasets.

Contribution

It proposes the SAoT framework that uses reasoning capabilities of large language models for implicit sentiment analysis, a novel approach in the field.

Findings

ERINE-Bot-4+SAoT achieves higher F1 scores than baselines.

The framework effectively analyzes implicit sentiments using reasoning.

Performance improvements are consistent across datasets.

Abstract

Implicit Sentiment Analysis (ISA) is a crucial research area in natural language processing. Inspired by the idea of large language model Chain of Thought (CoT), this paper introduces a Sentiment Analysis of Thinking (SAoT) framework. The framework first analyzes the implicit aspects and opinions in the text using common sense and thinking chain capabilities. Then, it reflects on the process of implicit sentiment analysis and finally deduces the polarity of sentiment. The model is evaluated on the SemEval 2014 dataset, consisting of 1120 restaurant reviews and 638 laptop reviews. The experimental results demonstrate that the utilization of the ERNIE-Bot-4+SAoT model yields a notable performance improvement. Specifically, on the restaurant dataset, the F1 score reaches 75.27, accompanied by an ISA score of 66.29. Similarly, on the computer dataset, the F1 score achieves 76.50, while the ISA score amounts to 73.46. Comparatively, the ERNIE-Bot-4+SAoT model surpasses the BERTAsp + SCAPt baseline by an average margin of 47.99%.