Recommending personalized events based on user preference analysis in event based social networks

Recently, a number of events have begun to be created and shared as event based social network becomes more active. Accordingly, methods for providing events that are suited to individual's interests are being studied through analysis of participation and sharing of events by users. In this paper, we propose a new personalized event recommendation method based on user preference analysis in event based social networks. The proposed method manages the recent preferences of users by taking into account information about the recent event participations and the circumstances of the users. Our method uses relationship analysis and collaborative filtering to predict values of user properties that cannot be evaluated otherwise. The proposed method suggests events only to users who are expected to join when new events occur, thus avoiding unwanted suggestions. A performance evaluation was conducted to show the superiority of the proposed event recommendation method. As a result of the performance evaluation, it was confirmed that the proposed method has precision and recall rates that are higher than those of the existing methods by 10-30%.