Application of Artificial Intelligence and Big Data Analytics for Personalized Cultural Tourism Experiences in Uzbekistan
Аннотация
Cultural personalization is a major concern for tourism authorities and experience designers, leading to a serious challenge to destination competitiveness and one of the major causes of low visitor engagement in the heritage-driven tourism sector of Uzbekistan. The present study aimed to assess intelligent recommendation systems and identified data-driven factors and their perceived impact on tourist satisfaction by using the AHP model and Structural Equation Modeling in the context of cultural tourism, Uzbekistan. Aiming at the customization of multi-dimensional experiences and prediction of single short stay tourist preferences, this study compares the predictive performance of the three AI-based analytics models on four dimensions: user behavior, interest tagging, semantic clustering, and location-aware recommendations, to verify the effectiveness of hybrid and adaptive personalization mechanisms and determine the most accurate inference method of short visit tourism data. In this framework, network analysis (Gephi platform) visualization is used to collect the data of interactional linkages among visitors and personalized thematic nodes, and then, the SEM-based AHP model is introduced to optimize the whole analytical process. The impacts such as cultural immersion (weighted 0.376) and historical authenticity (weighted 0.342) were the highest-ranking variables causing differentiation due to personalization depth. The results concluded that, in particular, narrative-based recommendations and geo-contextual filters seem more effective to localize content, so the long-term integration and algorithmic calibration in Uzbekistan for museums, heritage sites, and culinary trails contribute significantly to value creation in the tourism economy. The implications of this research imply for the development of adaptive analytics to establish intelligent cultural tourism systems used without the dependency on various manual curation efforts in local destinations.