Boosting a Smart Tourism Destination with Big Data techniques, sentiment analysis and geo-located information: a case study from inland Spain

The proliferation of social media has amplified the impact of online reputation on tourism destinations. This study proposes an innovative methodology based on Big Data techniques and geo-located information to develop a synthetic tourism online reputation index (TORI) to assess tourists’ perceptions of destinations. The methodology integrates the Cross-Industry Standard Process for Data Mining (CRISP-DM) and Knowledge Discovery in Databases (KDD) frameworks, ensuring a rigorous and efficient analysis of tourism sector data. An ontology is defined to categorize attraction points of tourist destinations, and Natural Language Processing (NLP) techniques are applied to conduct sentiment analyses of tourist reviews and analyze the tourist profile. The methodology is validated through a case study of the province of Burgos, Spain, demonstrating its practical application in strengthening the technological axis of the Smart Tourism Destination (STD) model and its potential to support sustainable tourism development in rural and sparsely populated areas. The results are presented in an interactive scorecard, facilitating data interpretation and strategic decision-making by tourism stakeholders. Overall, the study contributes to the literature by addressing key gaps, such as the lack of quantitative and standardized approaches to online reputation measurement, the need for a comprehensive index that encompasses all attraction points within a destination and the importance of offering a human-centered vision, focusing on tourist perceptions and experiences. In conclusion, the proposed methodology offers a data-driven approach for understanding and improving destination reputation, which is crucial for maintaining competitiveness and ensuring sustainable tourism development in the digital age.