Exploring computer supported collaborative coordination through social networks

Abstract

The performance of work groups and in particular geographically distributed ones is negatively affected by communication issues and task dependencies. Contemporary science suggests social link optimization apart from improving the technical aspects to address these issues. In our study, we focus on distributed coordination and project performance. Social network structure and coordination performance variables are described by our framework with regards to distributed coordination during bug fixing process. Based on the model and the literature reviewed, we propose two propositions-(i) the level of interconnectedness has a negative relation with coordination performance; and (ii) centrality social network measures have positive relation with coordination performance variables. We use a sample of 415 Open Source Projects hosted on SourceForge.net. The results suggest that both propositions are correct. Furthermore, in the methods section implementation of an automated process is introduced to build graph definitions in adjacency matrix or NCOL format from thousands of forum threads. We describe the implementation of a novel method to plot sociograms in batch from hundreds of graph definitions automatically and calculate network centrality and density measures for all of them at the same time. Finally, we suggest the implications of this study to software development project management research. © 2011 Elsevier Inc. All rights reserved.