Location-based service using ontology and collaborative recommendation

Location-Based service (LBS) provides the fundamental services for upcoming ubiquitous environments. However, most existing patterns for location service are driven and supported by a LBS service provider only but lacking of user participation and personalized recommendation. In this paper, we propose a novel intelligent location-based service to address these issues. Our solution is based on ontology which is utilized to model and represent knowledge about user´s individual preferences and place-related information. The ontology supports user participation as collective intelligence. By using this information, our recommender system models the relationship between user and place as a heterogeneous graph. We propose an Improved Random Walk algorithm which involves user´s current context information to infer most preferred places matching their interests. Our experiments show that the performance of our algorithm is significantly improved compared to the existing algorithms.