A Comparitive Study on Point-of-Interest Recommendation Techniques in Location-Based Social Network

Location-Based Social Networks (LBSNs) are a special form of social Web system where users can create social connections with other system users or register each time they visit a particular Point-of-Interest (POI) through so-called check-ins. Location information enables a closer knowledge of consumers' interests and behavior by bridging the gap between the digital and physical worlds. Large-scale geospatial dataset has sparked research into innovative recommender systems that aim to ease users' travel and social interactions. In this study, we give a thorough review of the work done on this subject in recent years. A novel structure is presented that is divided into four phases, subsequently we analyse each phase and the related work that corresponds to it. We propose a taxonomy to categorise the recommender systems based on these four factors. The potential and challenges that still exist in the field are also been highlighted.