This chapter provides a critical review of how geospatial intelligence (GeoAI) technologies have been integrated into tourism geography. As artificial intelligence (AI) and big data continue to reshape research methodologies, tourism geography has evolved from relying primarily on qualitative approaches to embracing advanced quantitative techniques and computational models. We highlight key GeoAI-driven applications, including the identification of tourist destinations, sensing of tourists’ emotions through text and image analytics, discovery of behavioral patterns from mobility data, and advanced decision-making tools for destination assessment, recommendation, and scenario simulation. Alongside these applications, we discuss the methodological innovations—from machine learning to convolutional neural networks and graph convolutional neural networks—that have enhanced spatial perception, cognition, and planning. We also examine persistent challenges in data integration, noise reduction, privacy, and the creation of truly multimodal, standardized tourism datasets. In addressing these issues, this chapter suggests future directions, including the improved fusion of diverse data sources, the integration of large language models, and the development of novel hybrid frameworks. Ultimately, this review demonstrates how GeoAI is reshaping tourism geography research and practice, fostering more efficient, accurate, and context-aware spatial insights.