Exploiting geographical location for team formation in social coding sites

Social coding sites (SCSs) such as GitHub and BitBucket are collaborative platforms where developers from different background (e.g., culture, language, location, skills) form a team to contribute to a shared project collaboratively. One essential task of such collaborative development is how to form a optimal team where each member makes his/her greatest contribution, which may have a great effect on the efficiency of collaboration. To the best of knowledge, all existing related works model the team formation problem as minimizing the communication cost among developers or taking the workload of individuals into account, ignoring the impact of geographical location of each developer. In this paper, we aims to exploit the geographical proximity factor to improve the performance of team formation in social coding sites. Specifically, we incorporate the communication cost and geographical proximity into a unified objective function and propose a genetic algorithm to optimize it. Comprehensive experiments on a real-world dataset (e.g., GitHub) demonstrate the performance of the proposed model with the comparison of some state-of-the-art ones. Copyright © 2017 Springer International Publishing AG.