A Conceptual Framework for Developing and Evaluating Personalized Tourist Recommendation Systems Using Large Language Models

Ioannis A. Nikas (), Athanasios Koutras () and Antonopoulou Theodora
Additional contact information
Ioannis A. Nikas: University of Patras
Athanasios Koutras: University of Peloponnese
Antonopoulou Theodora: University of Patras

A chapter in Innovation and Creativity in Tourism, Business and Social Sciences, 2025, pp 515-530 from Springer

Abstract: Abstract When planning for upcoming travel, it is essential to engage in systematic pre-trip preparation. To commence, travelers should first pinpoint their preferences, followed by conducting extensive research using various resources such as travel blogs, forums, tourism websites, social media platforms, and personal recommendations to compile a preliminary list of activities. Subsequently, these activities should be prioritized based on constraints such as time, budget, and accessibility, aligning with the travelers’ specific travel objectives. A detailed day-to-day itinerary should be developed, encompassing the prioritized activities while also allowing room for spontaneity and relaxation. Practical considerations like securing reservations, arranging transportation and accommodations, and planning appropriate clothing and gear should be addressed during this phase. Recent advancements in artificial intelligence (AI), particularly Large Language Models (LLMs) such as GPT-4, have significantly improved the process of travel planning. These advanced AI models offer personalized recommendations, streamline itinerary creation, and provide real-time updates. By analyzing travelers’ preferences and constraints, these tools suggest optimized plans, thus ensuring a tailored and dynamic approach to travel planning. This research proposes a comprehensive framework that integrates three key components: a survey designed to capture traveler profiles, interaction with an LLM for tailored recommendations, and an evaluation process focused on assessing satisfaction. A pilot study involving a two-stage survey has demonstrated the framework's potential to enhance travel planning by offering customized, dynamic, and highly satisfactory activity suggestions.

Keywords: Travel planning; Pre-trip preparation; Personalized recommendations; Artificial Intelligence (AI); Large Language Models (LLMs); Comprehensive framework (search for similar items in EconPapers)
JEL-codes: C45 C83 L83 O33 Z31 Z39 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prbchp:978-3-031-78471-2_20

Ordering information: This item can be ordered from
http://www.springer.com/9783031784712

DOI: 10.1007/978-3-031-78471-2_20

Access Statistics for this chapter

More chapters in Springer Proceedings in Business and Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().