Trust-aware Location Recommendation for User Groups

Recommender systems have become indispensable part of online environments. Product recommendations in ecommerce applications, location recommendations in location related applications, and user and post recommendations in online social networks are just a few examples in the world of online recommendations. The recommendations generated in such environments are mostly for individuals. However, increasing use of social networks and online communities lead to need for generating recommendations for a group of users for joint activities, such as eating out as a group or seeing a movie with friends. In the literature, there are studies proposing recommendation solutions for groups, but the number of such studies is very limited. In this work, we address the problem of location recommendation to a group of users, and the proposed solutions are based on Random Walk with Restart (RWR) algorithm on the social network graph. Another novel aspect of the proposed work is the use of trust factor of users in location-based social networks (LBSNs). In generating group recommendations, we follow two alternative paths. The first one aggregates the location recommendations that are generated with the Random Walk algorithm for each member in the group, taking the preferences and objectivity scores of the individuals into account. The second one is based on creating a group profile by blending preferences and venue category types, and using this group profile to run the Random Walk algorithm once. In both approaches trust factor of users is incorporated into the solutions within the social network graph. The experiments conducted on the data collected from the location based social network platform Foursquare have shown that the trust factor of users improves the performance of group recommendation system and the proposed algorithm provides recommendations to groups with high accuracy compared to the baselines.