Scholarlink

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 2,000 Amazon app reviews by comparing each method’s predictions to human judgments. CoT prompting improved classification accuracy from 84% to 93%, highlighting the benefit of explicit reasoning in enhancing sentiment analysis performance.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing Granular Sentiment Classification with Chain-of-Thought Prompting in Large Language Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Vihaan Miriyala,
  • Smrithi Bukkapatnam,
  • Lavanya Prahallad

摘要

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 2,000 Amazon app reviews by comparing each method’s predictions to human judgments. CoT prompting improved classification accuracy from 84% to 93%, highlighting the benefit of explicit reasoning in enhancing sentiment analysis performance.