用大模型识维度，传统方法批处理，高效分析百万级评论情感。
Beyond the Star Rating: A Scalable Framework for Aspect-Based Sentiment Analysis Using LLMs and Text Classification
- LLM找评价维度，经典机器学习批量做情感分类
- 分析470万条17年餐厅评论，维度与评分相关性显著
- 适合酒店、餐饮等服务行业做大规模客户反馈分析
顾客评论已成为商家和消费者的重要信息来源，但有效分析数百万条非结构化评论仍具挑战。尽管大语言模型（LLMs）在自然语言理解方面表现优异，但其在大规模评论分析中的应用受限于计算成本与可扩展性问题。本研究提出一种混合方法：使用LLM进行方面识别，同时采用经典机器学习方法实现大规模情感分类。基于ChatGPT对抽样餐厅评论的分析，识别出用餐体验的关键方面，并利用人工标注数据构建情感分类器，随后应用于某主流平台历时17年收集的470万条评论。回归分析显示，机器标注的方面能显著解释不同用餐体验维度、菜系及地理区域中整体评分的方差。结果表明，结合LLM与传统机器学习可有效实现大规模客户反馈的方面级情感分析，为旅游、餐饮等行业研究人员和从业者提供实用框架。
原文摘要 · Abstract (English)
Customer-provided reviews have become an important source of information for business owners and other customers alike. However, effectively analyzing millions of unstructured reviews remains challenging. While large language models (LLMs) show promise for natural language understanding, their application to large-scale review analysis has been limited by computational costs and scalability concerns. This study proposes a hybrid approach that uses LLMs for aspect identification while employing classic machine-learning methods for sentiment classification at scale. Using ChatGPT to analyze sampled restaurant reviews, we identified key aspects of dining experiences and developed sentiment classifiers using human-labeled reviews, which we subsequently applied to 4.7 million reviews collected over 17 years from a major online platform. Regression analysis reveals that our machine-labeled aspects significantly explain variance in overall restaurant ratings across different aspects of dining experiences, cuisines, and geographical regions. Our findings demonstrate that combining LLMs with traditional machine learning approaches can effectively automate aspect-based sentiment analysis of large-scale customer feedback, suggesting a practical framework for both researchers and practitioners in the hospitality industry and potentially, other service sectors.
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。