UGuideRAG: Intent-Enhanced Retrieval-Augmented Generation with User-Generated Content for Personalized Urban Tourism

Zhaonan Wang

Abstract: Citywalk, as an increasingly popular form of urban tourism, emphasizes immersive, diverse, and personalized exploration over conventional sightseeing. These features evolving tourist expectations pose new challenges for intelligent itinerary planning, particularly in capturing the rich experiential attributes of visitor attractions and aligning them with ambiguous and underspecified natural language queries. We propose UGuideRAG (User-Generated Content-Guided RAG), a modular framework that leverages usergenerated content to construct a comprehensive attraction database, employs large language models for intent-enhanced retrieval and recommendation, and incorporates spatial optimization to ensure coherent itinerary planning. By bridging the gap between partially expressed user goals and the multi-dimensional nature of urban experiences, UGuideRAG enables more insightful and personalized trip recommendations. Experiments on real-world datasets demonstrate that our framework consistently surpasses existing methods in producing contextually relevant, user-centered, and spatially optimized urban tourism itineraries.