Abstract
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.
Abstract (translated)
我们探讨了在大型语言模型（LLM）中使用链式思维（CoT）提示，以提高应用商店评论中的细粒度情感分类的准确性。传统的数值和极性评分方法往往无法捕捉到用户反馈中蕴含的细微情感。我们通过将每种方法的预测与人类判断进行比较，在2000条亚马逊应用评论上评估了CoT提示相较于简单提示的有效性。结果显示，CoT提示使分类准确率从84%提高到了93%，突显了明确推理在提升情感分析性能方面的优势。
URL
https://arxiv.org/abs/2505.04135
