用思维链提示提升应用评论情感分类准确率
Enhancing Granular Sentiment Classification with Chain-of-Thought Prompting in Large Language Models
- 让大模型逐步推理用户评论的情感逻辑
- 准确率从84%提升至93%
- 适合需要精细情感分析的场景
我们研究了在大型语言模型中使用思维链（Chain-of-Thought, CoT）提示，以提升应用商店评论中细粒度情感分类的准确性。传统评分体系常无法捕捉用户反馈中的细微情感。我们在2000条亚马逊应用评论上，对比了CoT提示与简单提示的效果，发现其预测结果与人工判断的吻合度显著提高，准确率由84%上升至93%，验证了显式推理对情感分析性能的增强作用。
原文摘要 · Abstract (English)
We explore the use of Chain-of-Thought (CoT) prompting with large language models (LLMs) to improve the accuracy of granular sentiment categorization in app store reviews. Traditional numeric and polarity-based ratings often fail to capture the nuanced sentiment embedded in user feedback. We evaluated the effectiveness of CoT prompting versus simple prompting on 2000 Amazon app reviews by comparing each method's predictions to human judgements. CoT prompting improved classification accuracy from 84% to 93% highlighting the benefit of explicit reasoning in enhancing sentiment analysis performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。