Inferring User Situations from Interaction Events in Social Media

With the advances of Internet technologies and an explosive growth in the popularity of social media, an increasingly large part of human life is getting digitized and becoming available on the web. This phenomenon brings opportunities and motivates us to infer users’ situations by exploiting their interaction events in various social media such as online social networks, blogs and email. One of the key requirements of inferring situations from interaction events is to consider both the semantic and temporal aspects of events in the situation inference process. In this paper, we address this issue and propose a novel approach to exploiting users’ interaction events in social media to infer their situations. We present an ontology-based interaction event model that captures the properties of users’ interaction activities in social media. We further provide a rule-based situation specification technique that integrates the interaction event ontology (for semantically matching interaction events) with temporal event relationships (for correlating historical interaction events). We also provide a platform to realize the situation reasoning/inference process, which combines semantic matching and complex event processing. We conduct a performance evaluation of the platform to quantify its efficacy. The feasibility and applicability of our approach is demonstrated by developing a socially aware phone call application as a case study.