Complementing Travel Itinerary Recommendation Using Location-Based Social Networks

We proposed in a previous work a recommendation system that, according to the requirements specified by its users, was capable of generating a few travel itineraries of distinct features (e.g. the most appealing itinerary, the shortest itinerary or the itinerary with the highest performance/price ratio) for user selection. We anticipated to complement the recommended travel itineraries by taking advantage of recent advances in location-acquisition and wireless communication technologies. With such technologies, people can share geo-spatial locations and location-based activities in the physical world via location-based social networks (LBSN), which makes it possible to help deduce a prospective traveler's dream destination using their check-ins published and shared on those websites. These user check-ins are informative in that a user's historical behaviors is a powerful indicator of his/her preferences. Therefore, we looked into and utilized user check-ins and social connections when building up a trip planner (such as our recommender) so as to better serve the travelers who may merely wander a travel website and seek the best vacation packages, flights, or hotel for their next trip. Our experiment verified the feasibility and efficiency of using user check-ins and social connections accessible from LBSNs in terms of discovering users' potential travel destination.