Event-aware analysis of cross-city visitor flows using large language models and social media data

Source abstract

Understanding the fluctuations of cross-city travel demand is crucial for the efficient operation of intercity transport systems. Public events, such as concerts and fireworks displays, can cause irregular surges in cross-city travel demand, leading to potential overcrowding, travel delays, and public safety concerns. To better anticipate and accommodate such demand surges, it is essential to estimate cross-city visitor flows with awareness of public events. While prior studies primarily focused on the impacts of a single mega event or disruptions around an individual venue, this study extends the scope by proposing a generalizable framework to analyze visitor flows under multiple concurrent events. We propose to leverage large language models (LLMs) to extract event features from multi-source online information and massive user-generated content on social media platforms. Specifically, social media popularity metrics are designed to capture the effects of online promotion and word-of-mouth in attracting visitors, with their effectiveness verified through comparative analysis. An event-aware machine learning model is then adopted to uncover the specific impacts of different event features and ultimately predict visitor flows for upcoming events. Using real-world events, social media, and visitor arrival data from Hong Kong, the framework is applied to predict daily flows of Chinese Mainland visitors, achieving a testing R-squared of over 85%. We further investigate the heterogeneous event impacts on visitor numbers across different event types and major travel modes. Both promotional popularity and word-of-mouth popularity are found to be associated with increased visitor flows, but the specific effects vary by the event type. This association is more pronounced among visitors arriving by metro and high-speed rail, while it has less effect on air travelers. Through a case study of a specific venue, we demonstrate how event-aware visitor flow prediction facilitates coordinated inter-agency measures and guides the development of specialized transport policies. Such analysis enables the implementation of targeted policies, including responsive operations of border control, dedicated shuttle services to event venues, and comprehensive on-site traffic management strategies.