Abstract

Artificial intelligence has a long history of learn-ing from domain problems ranging from chess to jeopardy. In this work, we look at a problem stem-ming from social science, namely, how do social relationships influence communication content and vice versa. The tools used to study communication content (content analysis) have rarely been com-bined with those used to study social relationships (social network analysis).  Furthermore, there is even less work addressing the longitudinal charac-teristics of such a combination. This paper presents a general framework for measuring the dynamic bi-directional influence between communication con-tent and social networks. The framework leverages the idea that knowledge about both kinds of net-works can be represented using the same knowl-edge representation. In particular, through the use of Semantic Web standards, the extraction of net-works is made easier. The framework is applied to two use-cases: online forum discussions and con-ference publications.  The results provide a new perspective over the dynamics involving both so-cial networks and communication content.