Classification-based Situational Reasoning for Task-oriented Mobile Service Recommendation

We study the case of integrating situational reasoning into a mobile service recommendation system. Since mobile Internet services are rapidly proliferating, finding and using appropriate services requires profound service descriptions. As a consequence, for average mobile users it is nowadays virtually impossible to find the most appropriate service among the many offered. To overcome these difficulties, task navigation systems have been proposed to guide users towards best-fitting services. Our goal is to improve the user experience of such task navigation systems by adding contextawareness (i.e., to optimize service navigation by taking the user’s situation into account). In this paper we propose the integration of a situational reasoning engine that applies classification-based inference to context elements, gathered from multiple sources and represented using ontologies. The extended task navigator enables the delivery of situation-aware recommendations in a proactive way. Initial experiments with the extended system indicate a considerable improvement of the navigator’s usability.