Navigating the smart tourism era: a systematic review of how intelligent systems are shaping the future of travel

Abstract

Tourism recommendation systems use artificial intelligence (AI), machine learning (ML), and data analytics to support travel decisions. This systematic literature review examines decision types, disciplinary distribution, themes, and research gaps in AI-based tourism recommendation research. Following the Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA) guidelines, we reviewed 75 Scopus indexed articles published between 2009 and 2025. The studies were classified into four decision types: Macro-Level destination guidance, Micro-Level place recommendations, Planning-Level itinerary and route planning, and Support & Service-Level recommendations. The findings show that research is concentrated in Micro-Level and Planning-Level recommendations, while Macro-Level and Support & Service-Level recommendations receive less attention. Most studies were published in computer science journals, with limited representation in tourism, business, and social science outlets. Keyword cooccurrence analysis identified six themes: applied analytics and social media, neural recommender systems and smart tourism, POI and route planning, classical ML techniques, tourism industry recommendation methods, and reinforcement learning-based trip planning. The findings identify future research opportunities to connect the four decision types across the travel journey, align data and system design with tourism-specific decisions and conditions, strengthen the use of tourism and business perspectives, and examine how emerging technologies can support traveler needs, tourism organizations, service coordination, and practical smart tourism applications. It contributes a decision oriented framework and future research agenda for tourism recommendation systems.