It is important for mobile service providers to be aware of user contexts and to provide contextually relevant mobile services to users. Thereby, in this paper, we propose a novel mechanism for integrating online social networks, which are regarded as an important channel for exchanging and propagating contexts. To efficiently discover personal contexts of certain users, the contexts of their neighbors can be fused to provide mobile recommendation services to mobile subscribers. However, since the social network of each user is distributed across several systems, it has been difficult to integrate contexts from distributed social networks. Thereby, we mobilize all possible on- and off-line social networks to build an ego-centric social network. We implemented the proposed system by collecting the social network dataset from online sources (e.g., Facebook, Twitter, CyWorld, and co-authoring patterns in major Korean journals) and offline (e.g., co-participation patterns in a number of Korean domestic conferences). After the system was implemented, we provided mobile services to conference participants by sending text messages about time schedules of relevant presentations.

mobile recommendation service, social network analysis, social network portability, sontext fusion