Enhancing Real-Time Adaptability in Tourism Recommendation Systems through Knowledge Graph Techniques: A Quantitative Study

Traditional tourism recommendation systems (TRS) often fail to deliver highly personalized, context-aware, and adaptive travel suggestions due to limitations in algorithmic complexity, fragmented data sources, and insufficient real-time processing capabilities. This study quantitatively examines how knowledge graph-based approaches can address these shortcomings by improving TRS performance in terms of accuracy, coverage, integration, and adaptability. Using a structured survey administered to 200 participants, including travelers and tourism industry stakeholders, the research measures perceptions of TRS effectiveness across ten key performance indicators, each assessed on a 5-point Likert scale. Data were analyzed using SPSS, applying descriptive statistics, correlation, regression, t-tests, and ANOVA to identify significant relationships and trends. Findings reveal moderate to strong agreement that knowledge graphs enhance TRS efficiency by integrating heterogeneous data, reducing information overload, and enabling hybrid methodologies combining machine learning with semantic data modeling. However, results also show variability in perceptions, particularly regarding the tangible benefits of real-time adaptability, suggesting that user experience and awareness significantly influence evaluations. While participants generally support increased investment in knowledge graph technologies, the initial reliability analysis indicated the need for refinement of survey items to improve internal consistency. Overall, the study provides empirical evidence that integrating knowledge graphs into TRS can support more dynamic, personalized, and contextually relevant recommendations, ultimately contributing to improved user satisfaction and competitive advantage for tourism service providers. These insights inform practical strategies for designing next-generation TRS architectures capable of adapting in real-time to evolving traveler needs and environmental changes.