An Intelligent Tourism Recommender System Using Retrieval-Guided Large Language Models

Authors

• Wei-Jun Lim, Multimedia University, Malaysia
• Nabhan D. Salih, Ohio State University, USA
• Hairulnizam Mahdin, Universiti Tun Hussein Onn Malaysia, Malaysia
• Ammar Alazab, Torrens University, Australia

Corresponding Author ORCID Identifer

Ammar Alazab https://orcid.org/0000-0001-9443-937X

Section

Regular Issue

Abstract

Travel planning has become more complex nowadays due to the information overload from numerous online platforms causing travelers to be overwhelmed when selecting destinations, accommodations, and activities that match their preferences and constraints. Traditional tourism recommender systems usually provide static and generic suggestions that fail to match users’ needs and cannot understand natural user language. This research develops and evaluates a Generative AI Chatbot for Tourism Recommendations that use Large Language Models (LLMs) to generate personalized travel itineraries through natural language interaction to solve these limitations. The system can process user natural language inputs including travel origin and destination, trip duration and dates, and budget in a conversational way. This research used the TravelPlanner dataset which contains real-world tourism information on attractions, restaurants, accommodations, and flights. The chatbot uses carefully designed prompts with strict generation rules to produce day-by-day itineraries that match user constraints. The preliminary results show the system’s capability to generate human–readable travel plans that include correct flight selections, accommodation recommendations, and structured daily activities. The chatbot prototype also supports conversational refinement which allows users to modify their itineraries interactively. The evaluation was conducted using Bilingual Evaluation Understudy (BLEU) and Recall-Oriented Understudy for Gisting Evaluation - Longest Common Subsequence (ROUGE-L) metrics to measure response quality and achieving a BLEU score of 0.59, ROUGE-L of 0.68, and constraint accuracy of 93%. This research has contributed to AI-driven tourism planning by showing how generative AI can be used to create interactive and context-aware assistants in recommender systems. Future work will focus on including external APIs and conducting a comprehensive user testing to measure the usability and satisfaction level in the real world.

Cite This Article

Lim, W.-J., D. Salih, N., Mahdin, H., & Alazab, A. An Intelligent Tourism Recommender System Using Retrieval-Guided Large Language Models. Journal of Informatics and Web Engineering, 5(3), 339–356. https://doi.org/10.33093/jiwe.2026.5.3.21

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.