Forecasting Tourism Demand: A Bibliometric Review of Trends, Methodologies, and Big Data Integration (2015-2024)

This study aims to provide a bibliometric review of trends, methodologies, and the integration of big data in Tourism Demand forecasting from 2015 to 2024. Bibliometric analysis is conducted to map the development of literature focusing on the latest techniques in Tourism Demand forecasting, with an emphasis on the application of big data and Artificial Intelligence technologies, particularly deep learning models based on CNN and LSTM. Data cleaning was performed using OpenRefine, while keyword clustering and visualization were carried out with VOSviewer to identify key trends in this research. The analysis shows a significant surge in publications related to deep learning and big data since 2018, peaking in 2020. Deep learning models, such as CNN and LSTM, have begun to dominate Tourism Demand forecasting research due to their ability to handle non-linear patterns that traditional models cannot address. Additionally, the increased use of real-time data, such as "Google Trends" and "social media," reflects a shift towards utilizing big data in Tourism Demand forecasting. These findings provide valuable insights for practitioners and policymakers to plan policies and allocate resources in the dynamic tourism sector by integrating advanced technologies.