Proceedings
Copyright © 2025 for the individual papers by the papers’ authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). This volume is published and copyrighted by its editors. The copyright for papers appearing in these proceedings belongs to the papers’ authors.
This volume is published by Julia Neidhardt, Tsvi Kuflik, Amit Livne, Markus Zanker & Wolfgang Wörndl. Proceedings of the Workshop on Recommenders in Tourism (RecTour 2025), held in conjunction with the 19th ACM Conference on Recommender Systems (RecSys 2025), September 22nd – 26th, 2025, Prague, Czech Republic, https://recsys.acm.org/recsys25/.
Julia Neidhardt, Tsvi Kuflik, Amit Livne, Markus Zanker & Wolfgang Wörndl (editors).
Further information about the workshop can be found at: https://workshops.ds-ifs.tuwien.ac.at/rectour25/ This volume contains the contributions of the Workshop on Recommenders in Tourism (RecTour), organized in conjunction with the 19th ACM Conference on Recommender System (RecSys 2025) in Prague, Czech Republic. RecTour 2025 highlights the unique challenges associated with developing recommender systems for the tourism industry. Unlike simple item-matching systems, tourism presents complex scenarios where travelers plan vacations involving interdependent product bundles - such as transportation, accommodations, attractions, and activities - each with limited availability and influenced by various contextual factors (e.g., spatiotemporal, social, and environmental contexts, as well as the sequence of activities). These factors significantly affect decision-making, which is often emotionally driven and experiential rather than purely rational or objective.
Providing timely and relevant information about destinations, accommodations, and services is particularly challenging in this context. Moreover, many tourism information providers are small or medium-sized enterprises (SMEs) that lack the resources to implement even basic recommendation systems. The absence of standardized data formats further complicates system development. Additionally, tourism products are often co-produced during the interaction between the consumer and provider, making the context of recommendations critically important.
The rapid advancement of information and communication technologies (ICT), especially the web, has revolutionized tourism, reducing travelers’ reliance on traditional travel agents. Studies show that travelers now actively use ICT to craft personalized vacation packages, often seeking free, real-time information on-site instead of relying on potentially outdated and costly visitor guides. However, the abundance of online information can lead to information overload, making recommender systems a valuable tool for streamlining the decision-making process. Despite their potential, designing effective recommender systems for the tourism sector remains a formidable task due to its complexity. This workshop brings together researchers and practitioners from diverse fields - such as tourism, recommender systems, user modeling, human-computer interaction, mobile and ubiquitous technologies, artificial intelligence, and web information systems - who are engaged in the tourism recommendation domain. The event aims to foster discussion on innovative solutions to the specific challenges faced in this area and to advance the state-of-the-art in tourism recommender systems. Additionally, it seeks to explore practical applications of these technologies from the perspectives of individual users, user groups, service providers, and other stakeholders, including destination management organizations and government agencies.
Finally, RecTour 2025 aims to build on the community engagement and dialogues initiated in previous workshops, continuing to strengthen collaboration and innovation within this dynamic field.
• Julia Neidhardt, Christian Doppler Laboratory for Recommender Systems, TU Wien, Austria • Tsvi Kuflik, Information Systems Department, The University of Haifa, Israel • Amit Livne, Booking.com, Tel Aviv, Israel • Markus Zanker, Free University of Bozen/Bolzano, Italy and University of Klagenfurt, Austria • Wolfgang Wörndl, Technical University of Munich (TUM), Germany Program Committee • Alejandro Bellogin, Universidad Autonoma de Madrid • Derek Bridge, University College Cork • Linus W. Dietz, King’s College London • Damianos Gavalas, University of Aegean • Dietmar Jannach, University of Klagenfurt • Dominik Kowald, Know-Center • Jan Krasnodebski, Hostelworld Group • Antonio Moreno, Universitat Rovira i Virgili • Thuy Ngoc Nguyen, University of Dayton • Francesco Ricci, Free University of Bozen-Bolzano • Pablo Sánchez, Universidad Pontificia Comillas
Acknowledgement
Keynote Presentation: Recommender Systems in Tourism through a Fair and Sustainable
Recommender systems increasingly shape how people travel – what destinations are visited, where to stay, and which experiences to choose. These decisions carry significant environmental, social, and cultural consequences, from carbon emissions and over-tourism to the survival of local communities. This talk examines recommender systems in tourism through a fair and sustainable lens, highlighting the challenges of accountability, fairness, and transparency in guiding responsible travel choices. Drawing on a framework for tangible recommendations, it frames tourism recommendations as not just digital suggestions but embodied decisions with lasting consequences. The talk outlines pathways toward accountability-aware, fair, and consequence-sensitive recommender design that can support more sustainable and responsible forms of tourism.
Alan Said is an Associate Professor of Computer Science at the University of Gothenburg, Sweden, specializing in human-centered AI, recommender systems, user modeling, and AI sustainability. His research spans machine learning theory, health applications, personalization, and interdisciplinary work on fairness, transparency, and environmental impact. He earned his Ph.D. from TU Berlin on recommender system evaluation and held Marie Curie Fellowships at CWI and TU Delft, alongside industry roles in applied ML. Author of 100+ publications, he has received awards including the Springer Best Paper Award at UMAP. Said serves as ACM RecSys Steering Committee Chair and in multiple editorial and leadership roles.
08:30 - 08:45 Welcome 08:45 - 09:30 Keynote Alan Said: Recommender Systems in Tourism through a Fair and Sustainable Lens 09:30 - 10:30 Paper Presentations – Apostolos Avranas, Moaad Maaroufi, Alix Lheriter, Rodrigo Acuna Agost and Eoin Thomas: Mix It Up: Improving Performance in Travel Choice Modeling – Yuuki Tachioka: KP4POI: Efficient POI Recommendation on Large-scale Datasets via Knowledge Prompting of Venues and Users – Joanna Zamiechowska, Julia Neidhardt and Wolfgang Wörndl: CiRi-Engine: POI Recommender System for Diverse and Balanced Walking Tours 10:30 - 11:00 Coffee Break 11:00 - 12:00 Paper Presentations – Ioannis Partalas: Simple Regularization for Aligning Embedding Spaces for Cross-brand Recommendation – Akshat Tandon and Ashmi Banerjee: Evaluating User Intent Classification and Hybrid Retrieval in a RAG-based Conversational Tourism Recommendation System – Elena L. González-Sanz, Iván Cantador and Alejandro Bellogín: LLM-based Generation of Personalized, Contextaware City Tourist Itineraries: A User Study with GPT Trip Planner 12:00 - 12:30 Group Discussion on „Generative AI for Tourism Recommender Systems“ and Closing