A semantic and structural similarity approach to personalize location-based services

In this paper the problem of refining user queries on a trader of location-based services (LBSs) is faced by using two kinds of similarity (structural and semantic). LBSs typically concentrate on providing users with information about points of interest or on the support for navigation and routing tasks. Personalization is a key feature of LBSs that improves their usability and involves a process of gathering user information during interaction with the user. This information can be used to deliver appropriate content and services, tailor made to the user's needs. The approach proposed in the paper can be applied to any kind of location-based services, it is independent from the specific domain, it takes into account spatial information and, finally, it allows the user profiles to be acquired explicitly and implicitly.