Paper Type
Short
Paper Number
PACIS2025-1704
Description
The increasing demand for personalised travel experiences has driven the need for intelligent systems capable of automating itinerary planning. Traditional recommendation platforms often lack adaptability to individual preferences and real-time constraints, limiting their effectiveness. This paper presents a context-aware intelligent tourist assistant that generates personalised travel itineraries, dynamically adjusting to POI availability and external factors. It contributes to the digital transformation of the tourism industry by automating travel planning through AI-driven personalisation and real-time adaptability. The system applies NLP, sentiment analysis and graph-based optimisation to build user interest profiles from chatbots, social media and surveys, integrating preference modelling and VRPTW-based route optimisation. Experiments confirm that AI-generated itineraries adapt dynamically, improving efficiency over manual planning. This work advances AI-driven travel planning, integrating adaptive recommendations and heuristic route optimisation, with future improvements in preference refinement and augmented reality integration.
Recommended Citation
Klimek, Radoslaw, "Context-aware Intelligent Tourist Assistant" (2025). PACIS 2025 Proceedings. 1.
https://aisel.aisnet.org/pacis2025/transform/transform/1
Context-aware Intelligent Tourist Assistant
The increasing demand for personalised travel experiences has driven the need for intelligent systems capable of automating itinerary planning. Traditional recommendation platforms often lack adaptability to individual preferences and real-time constraints, limiting their effectiveness. This paper presents a context-aware intelligent tourist assistant that generates personalised travel itineraries, dynamically adjusting to POI availability and external factors. It contributes to the digital transformation of the tourism industry by automating travel planning through AI-driven personalisation and real-time adaptability. The system applies NLP, sentiment analysis and graph-based optimisation to build user interest profiles from chatbots, social media and surveys, integrating preference modelling and VRPTW-based route optimisation. Experiments confirm that AI-generated itineraries adapt dynamically, improving efficiency over manual planning. This work advances AI-driven travel planning, integrating adaptive recommendations and heuristic route optimisation, with future improvements in preference refinement and augmented reality integration.
Comments
Transformation