A novel ChatGPT-based multimodel framework for tourism review mining: a case study on China’s five sacred mountains

Abstract

Purpose

This study aims to introduce an innovative framework for mining tourism reviews that not only excels in sentiment analysis accuracy but also prioritizes user-friendly design for enhanced usability.

Design/methodology/approach

Online reviews of China’s Five Sacred Mountains were analyzed using an integrated methodology. Sentiment analysis was performed using ChatGPT, bidirectional encoder representations from transformers (BERT) and convolutional neural networks, with ChatGPT demonstrating superior performance. Latent Dirichlet allocation extracted key attributes. Models including importance–performance analysis (IPA), asymmetric impact-performance analysis (AIPA) and importance–performance competitor analysis (IPCA) then synthesized findings.

Findings

The results demonstrate that ChatGPT outperforms both machine learning and lexicon-based models in sentiment recognition, exhibiting performance comparable to that of the BERT model. In the case study, integrating sentiment analysis outcomes with IPA reveals deficiencies in both topics and attributes. Moreover, the synergistic combination of IPA, AIPA and IPCA furnishes actionable recommendations for resource management and enables nuanced monitoring of sustainability attributes.

Practical implications

Leveraging this framework in conjunction with the ChatGPT platform for application development can bring practical convenience to the tourism industry. It supports sentiment analysis, topic categorization and opinion mining. Equipped with monitoring capabilities, it provides valuable insights for sustainable improvement, aiding managers in formulating effective marketing strategies.

Originality/value

This research develops a novel multimodel framework integrating various ML/DL techniques and business models in a synergistic way. It provides an innovative and highly accurate yet simple approach to tourism review mining and enhances accessibility of advanced artificial intelligence for sustainable tourism monitoring, addressing limitations of prior methods.

研究目的

本研究旨在引入一种创新的框架, 用于挖掘旅游评论, 不仅在情感分析准确性方面表现出色, 而且还优先考虑用户友好设计, 以提升可用性。

研究方法

本研究使用综合方法分析了中国五岳的在线评论, 使用ChatGPT进行情感分析。LDA提取了关键属性。然后, 包括IPA、AIPA和IPCA在内的模型综合了研究结果。

研究发现

结果表明, ChatGPT在情感识别方面优于机器学习和基于词典的模型, 表现与BERT模型相当。在案例研究中, 将情感分析结果与IPA结合起来揭示了主题和属性的不足。此外, IPA、AIPA和IPCA的协同组合为资源管理提供了可行的建议, 并实现了对可持续属性的细致监控

实践意义

结合ChatGPT平台在应用开发中利用该框架可以为旅游业带来实际便利。它支持情感分析、主题分类和意见挖掘。配备了监控功能, 为可持续改进提供了宝贵的见解, 帮助管理者制定有效的营销策略。

研究创新

本研究开发了一种新颖的多模型框架, 将各种ML/DL技术和商业模型以协同方式整合在一起。它提供了一种创新而高度准确但简单的方法, 用于旅游评论挖掘, 并提升了高级AI的可访问性, 以实现可持续旅游监测。

Citation

Cheng, X., Chen, Y., Wang, P., Zhou, Y., Wei, X., Luo, W. and Duan, Q. (2024), "A novel ChatGPT-based multimodel framework for tourism review mining: a case study on China’s five sacred mountains", Journal of Hospitality and Tourism Technology, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/JHTT-06-2023-0170