Work in progress - towards a tool to analyze qualitative aspects of the relations among members of social networks

This paper discusses a tool to study the relations among group members of a social network that evolve using a virtual environment. Understanding how these relations are built and maintained is essential to foster favorable conditions that can facilitate collective and individual learning. The focus of interest is how inner relations affect both the collective and individual learning of its members. We consider a group as being a set of relations among people and artifacts. As an example, we might determine which relations among members of a Project Team (predominantly goal-oriented) are different from the ones found in Communities of Practice (predominantly learning-oriented), and how they affect the learning of their members. We propose to characterize the relations among members by analyzing text content of social exchanges (e.g. email messages, blog posts, chat sessions, etc). The approach originality relies on taking into account the distinct points of view of its actors. Due to the distributed character of the problem (a virtual group), we intend to develop this tool by using a Multi- Agent System, whose architecture we present in this paper.