Reputation assessment and visitor arrival forecasts for data driven tourism attractions assessment

A new framework leveraging social media and big data successfully forecasts online reputation and visitor arrivals at UNESCO World Heritage Sites, including the Pont du Gard (Roman Aqueduct). Using machine learning, deep learning, causality assessment, and explainable AI, researchers identified key variables influencing predictions. A multilingual sentiment analysis tool based on transformers compared data from platforms like TripAdvisor and Twitter, while causality analysis revealed temporal impacts of social media posts on visitor numbers. This work, part of the Herit-Data project funded by the European Commission, demonstrates how advanced analytics can optimize tourism management for heritage sites.

Collini, E., Nesi, P., & Pantaleo, G. (2023). Reputation assessment and visitor arrival forecasts for data driven tourism attractions assessment. Online Social Networks and Media, 37-38, 100274. https://doi.org/10.1016/j.osnem.2023.100274