基于思维链提示的隐式情感分析
Implicit Sentiment Analysis Based on Chain of Thought Prompting
AI总结：
本文针对隐式情感分析问题，受思维链启发提出了SAoT框架，通过分析隐式方面与观点并反思推导情感极性，结合ERNIE-Bot-4模型在SemEval 2014数据集上显著超越基线并提升了各项指标。
摘要：
隐式情感分析（ISA）是自然语言处理中的一个重要研究领域。受大语言模型思维链（CoT）思想的启发，本文提出了一种思考情感分析（SAoT）框架。该框架首先利用常识和思维链能力分析文本中的隐式方面和观点。然后，它对隐式情感分析的过程进行反思，最后推导出情感极性。该模型在SemEval 2014数据集上进行了评估，该数据集包含1120条餐厅评论和638条笔记本电脑评论。实验结果表明，使用ERNIE-Bot-4+SAoT模型取得了显著的性能提升。具体而言，在餐厅数据集上，F1分数达到75.27，ISA分数为66.29。类似地，在计算机数据集上，F1分数达到76.50，而ISA分数为73.46。相比之下，ERNIE-Bot-4+SAoT模型以47.99%的平均优势超越了BERTAsp + SCAPt基线。
英文摘要：
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%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
