Context-Aware Recommendation for Smart Tourism: A Framework for Enhancing Archaeological Park Experiences

Smart city environments increasingly integrate digital technologies, sensing infrastructures, and intelligent data-driven services to improve citizens' quality of life and enhance urban experiences. Within this context, cultural heritage sites and archaeological parks represent important components of smart tourism ecosystems, where personalized and context-aware services can significantly improve visitor engagement. This paper presents a framework designed to enhance cultural experiences in archaeological parks through a Context-Aware Recommender System (CARS). The proposed framework integrates heterogeneous contextual data collected from IoT infrastructures, environmental sensors, and user devices, combining them within a layered framework composed of acquisition, knowledge management, inference, and application components. The recommendation engine is based on a Contextual Bias Matrix Factorization (CBMF) model that exploits embedded contextual information to predict user preferences and suggest relevant Points of Interest. The effectiveness of the proposed approach is evaluated through experiments conducted on three widely used context-aware datasets: DePaulMovies, LDOS-CoMoDa, and Travel-STS. The results show that the proposed method achieves competitive performance compared with state-of-the-art context-aware recommendation techniques, demonstrating its potential for improving user experiences in cultural heritage environments.