This is the authors' abstract. We don't add key points for this paper.
Empirical research has shown that incorporating big data into tourism and hospitality forecasting significantly improves prediction accuracy. This study presents a comprehensive review of big data forecasting in the tourism and hospitality industry, critically evaluating existing research and identifying five key research questions and trends that require further attention. These include the lack of theoretical foundation, the rise of high-frequency forecasting research, less attention to unstructured data, the necessity of dynamic data analysis in forecasting, and the construction of a tourism and hospitality demand information system based on cloud computing. Importantly, this study constructs a theoretical framework by combining relevant theories from psychology, communication, information processing, and other fields. Five types of big data used for tourism and hospitality forecasting are identified: web-based volume data, social media statistics, textual data, photo data, and video data. Additionally, more recent tactics such as mixed data sampling and machine learning methods are discussed.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Wu et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: