Nowadays, location-based social network (LBSN) has become one of the most popular applications with the rapid development of mobile Internet. However, due to the spatial and real-time properties, mobile service recommendation under LBSN environment faces too many challenges especially data sparsity problem. To tackle these challenges, a recommendation framework is proposed in this paper which has four layers defined as data collection layer, user profile modeling layer, information processing layer and recommendation feedback layer, respectively. Furthermore, the ISC-CF algorithm is implemented to integrate users’ interest profile, social influence and current location context to effectively overcome the data sparsity problem. Thus, the social influence is quantified by a modified measure way. Finally, a dynamic and personalized adjustment algorithm is built by using the users’ profile tracking and the current location context. The experiment results show that the algorithm proposed in this paper has significantly superior performance compared with the other baseline recommendation methods in both hometown area and out-of-town area.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.