Beyond the Star Rating: A Scalable Framework for Aspect-Based Sentiment Analysis Using LLMs and Text Classification

2026-02-24

AI Summary

This study addresses the challenge of performing efficient fine-grained sentiment analysis on large-scale unstructured customer reviews. To this end, the authors propose a hybrid architecture that integrates large language models (LLMs) with traditional machine learning: ChatGPT is employed to extract aspect dimensions from reviews, and a lightweight classifier trained on human-annotated data is then used to conduct aspect-level sentiment labeling across 4.7 million restaurant reviews. The approach achieves high accuracy while significantly improving scalability and computational efficiency, thereby overcoming deployment bottlenecks associated with pure LLM-based solutions. The resulting sentiment labels effectively explain variance in overall ratings across different cuisines, geographic regions, and dining dimensions, demonstrating the framework’s practical utility and effectiveness in real-world business applications.

Technology Category

• Natural Language Processing: Text Classification & Sentiment Analysis
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• aspect-based sentiment analysis
• large language models
• scalability
• customer reviews
• text classification

Innovation

• Aspect-Based Sentiment Analysis
• Large Language Models
• Scalable Framework
• Hybrid Approach
• Text Classification