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.