Doris Chenguang Wu , Wenjia Li , Ji Wu , Mingming Hu , Shujie Shen
{"title":"ChatGPT预测旅游需求的准确度如何?","authors":"Doris Chenguang Wu , Wenjia Li , Ji Wu , Mingming Hu , Shujie Shen","doi":"10.1016/j.tourman.2024.105119","DOIUrl":null,"url":null,"abstract":"<div><div>ChatGPT has demonstrated remarkable capabilities across various natural language processing (NLP) tasks. However, its potential for forecasting tourism demand from temporal data, specifically historical tourism arrivals data, remains an unexplored frontier. This research presents the first attempt to conduct an extensive Zero-shot and Chain-of-Thought analysis of ChatGPT's capabilities in tourism demand forecasting, under various temporal scenarios. Based on the Macau inbound tourism arrivals dataset, our empirical findings indicate that the predictive capability of ChatGPT-4 is noteworthy compared to the three benchmark time series models (Naïve, Exponential Smoothing, SARIMA) and the three benchmark machine learning models (Random Forest, Multi-Layer Perceptron, Long Short-Term Memory), especially when the forecast horizon is relatively short. Furthermore, compared to Zero-shot prompts, engaging in continuous dialogue can enhance the forecast accuracy of ChatGPT-4. This performance of ChatGPT highlights its potential for quantitative data prediction as a new user-friendly and cost-effective management tool.</div></div>","PeriodicalId":48469,"journal":{"name":"Tourism Management","volume":"108 ","pages":"Article 105119"},"PeriodicalIF":10.9000,"publicationDate":"2024-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"How well can ChatGPT forecast tourism demand?\",\"authors\":\"Doris Chenguang Wu , Wenjia Li , Ji Wu , Mingming Hu , Shujie Shen\",\"doi\":\"10.1016/j.tourman.2024.105119\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>ChatGPT has demonstrated remarkable capabilities across various natural language processing (NLP) tasks. However, its potential for forecasting tourism demand from temporal data, specifically historical tourism arrivals data, remains an unexplored frontier. This research presents the first attempt to conduct an extensive Zero-shot and Chain-of-Thought analysis of ChatGPT's capabilities in tourism demand forecasting, under various temporal scenarios. Based on the Macau inbound tourism arrivals dataset, our empirical findings indicate that the predictive capability of ChatGPT-4 is noteworthy compared to the three benchmark time series models (Naïve, Exponential Smoothing, SARIMA) and the three benchmark machine learning models (Random Forest, Multi-Layer Perceptron, Long Short-Term Memory), especially when the forecast horizon is relatively short. Furthermore, compared to Zero-shot prompts, engaging in continuous dialogue can enhance the forecast accuracy of ChatGPT-4. This performance of ChatGPT highlights its potential for quantitative data prediction as a new user-friendly and cost-effective management tool.</div></div>\",\"PeriodicalId\":48469,\"journal\":{\"name\":\"Tourism Management\",\"volume\":\"108 \",\"pages\":\"Article 105119\"},\"PeriodicalIF\":10.9000,\"publicationDate\":\"2024-12-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Tourism Management\",\"FirstCategoryId\":\"91\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0261517724002383\",\"RegionNum\":1,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENVIRONMENTAL STUDIES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tourism Management","FirstCategoryId":"91","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0261517724002383","RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL STUDIES","Score":null,"Total":0}
ChatGPT has demonstrated remarkable capabilities across various natural language processing (NLP) tasks. However, its potential for forecasting tourism demand from temporal data, specifically historical tourism arrivals data, remains an unexplored frontier. This research presents the first attempt to conduct an extensive Zero-shot and Chain-of-Thought analysis of ChatGPT's capabilities in tourism demand forecasting, under various temporal scenarios. Based on the Macau inbound tourism arrivals dataset, our empirical findings indicate that the predictive capability of ChatGPT-4 is noteworthy compared to the three benchmark time series models (Naïve, Exponential Smoothing, SARIMA) and the three benchmark machine learning models (Random Forest, Multi-Layer Perceptron, Long Short-Term Memory), especially when the forecast horizon is relatively short. Furthermore, compared to Zero-shot prompts, engaging in continuous dialogue can enhance the forecast accuracy of ChatGPT-4. This performance of ChatGPT highlights its potential for quantitative data prediction as a new user-friendly and cost-effective management tool.
期刊介绍:
Tourism Management, the preeminent scholarly journal, concentrates on the comprehensive management aspects, encompassing planning and policy, within the realm of travel and tourism. Adopting an interdisciplinary perspective, the journal delves into international, national, and regional tourism, addressing various management challenges. Its content mirrors this integrative approach, featuring primary research articles, progress in tourism research, case studies, research notes, discussions on current issues, and book reviews. Emphasizing scholarly rigor, all published papers are expected to contribute to theoretical and/or methodological advancements while offering specific insights relevant to tourism management and policy.