ABSTRACT Tourism places increasing pressure on coastal cities, where seasonal congestion, fragmented urban development and changing citizen expectations challenge the sustainability of services and governance. To address these issues, we present TorreviejaSensing, a social sensing framework that transforms user‐generated content into actionable evidence for policy and planning. The system combines multilingual natural language processing over X (Twitter) posts and Google Maps reviews, a policy‐aware mapping of social signals to municipal strategic axes and a retrieval‐augmented generation (RAG) chatbot that provides transparent evidence‐grounded answers to policy queries. Applied to Torrevieja (Spain), the framework enables real‐time tracking of mobility and cleanliness complaints, early detection of seasonal pain points and alignment of digital discourse with institutional strategies. A mixed‐methods evaluation—including manual annotation of NLP outputs, baseline comparison and a pilot human assessment of chatbot responses—demonstrates both robustness and practical utility. Findings reveal strong seasonal dynamics, recurrent topic clusters consistent with known governance challenges and improved transparency of the RAG assistant compared to keyword‐only approaches. Beyond the Torrevieja case, the framework is low‐cost, transferable and provides a replicable model for integrating citizen discourse into sustainable urban tourism governance.
Lucia et al. (Thu,) studied this question.