Knowledge-driven spatial competitive intelligence for tourism

Competition among tourism enterprises is an ineluctable component of sustainable tourism growth, requiring comprehensive studies to understand its dynamic and develop appropriate strategies. The literature employs text mining or statistical analyses to identify correlations between tourism areas as competitive relationships. However, this approach may not be fully applicable, due to the sparsity of crucial coexistence phenomena, and may fail to investigate fine-grained attractions' competition inside destination using large-scale geospatial data. To overcome the limitations, this study proposes a knowledge-driven competitive intelligence framework for tourism management, utilizing knowledge graph (KG) construction and inference technologies. First, multi-mode heterogeneous tourism data are integrated into a unified KG, including tourist check-in, online text, and basic geographic information. Second, the spatial-dependent GNN-based model absorbing abundant spatial semantic knowledge from tourism-oriented KG can enhance the performance of competition reasoning. Third, with multiple analyses via symbolic queries on KG, a comprehensive panorama of competition situations can be revealed.