Community Trajectory: Discovery of Evolutionary Collaboration Patterns Based on Event Co-participation

This paper presents a framework for analyzing and summarizing collaborative activities in a highly dynamic, context-rich social network. In everyday work, collaboration is essential, and people need to be aware of the activities of their peers to find opportunities for collaboration. Understanding activities of one’s peers become particularly difficult when people collaborate across time, locations or even disciplines. We propose to support collaboration by extracting and representing collaborative patterns, thus improve awareness. There are three key contributions in this paper: (a) a probability model for extracting the clustering structure of social interaction within a collaborative event context, (2) collaboration analysis for determining key people, events, and the strength of ties based on conditional probabilities, and (3) a dynamic, interactive visual representation that reveals “community trajectory” which supports exploration of temporal collaborative patterns. Our experiments using real-world collaborative event data reveals subgroup evolution and typical characteristics of collaborative projects, indicating the utility of our approach for supporting reflection on collaborative activities.