Mobile Context Provider for Social Networking

Abstract

Abstract. The ability to infer user context based on a mobile device together with a set of external sensors opens up the way to new contextaware services and applications. In this paper, we describe a mobile context provider that makes use of sensors available in a smartphone as well as sensors externally connected via bluetooth. We describe the system architecture from sensor data acquisition to feature extraction, context inference and the publication of context information to well-known social networking services such as Twitter and Hi5. In the current prototype, context inference is based on decision trees, but the middleware allows the integration of other inference engines. Experimental results suggest that the proposed solution is a promising approach to provide user context to both local and network-level services.

From IR to Mobile IR

“…The main difference across the proposed architectures are about (i) the range and type of sensors, (ii) the context inference engine, and (iii) the services supported by the middleware. For instance, Santos et al [162] introduce a platform integrating sensors already embedded in the mobile device with external ones connected via Bluetooth (in the paper a vest and backpack prototypes are presented). The framework allows the plug-in of different external inference engines as well.…”