TravelWithFriends: a hybrid group recommender system for travel destinations
Toon De Pessemier, Jeroen Dhondt, Kris Vanhecke, Luc Martens · Ghent University Academic Bibliography (Ghent University) · 2015
Recommender systems have proven their usefulness in many classical domains such as movies, books, and music to help users to overcome the information overload problem.But also in more challenging fields, such as tourism, recommender systems can act as a supporting tool for decision making when planning a trip.This paper proposes such a system providing group recommendations for travel destinations based on the users' rating profile, personal interests, and specific demands for their next destination.The proposed solution follows a hybrid approach, combining contentbased, collaborative filtering, and knowledge-based strategies.Since traveling is often a group activity, families and groups of friends can receive group recommendations based on their combined profiles.The recommender system is tested in a prototype web application and evaluated by a group of test users.The results prove the usefulness of recommendations for travel destinations and show that the hybrid system outperforms each individual technique.