A Comparative Study of Team Formation in Social Networks

Team formation in social networks is a fundamental problem in many database or web applications, such as community-based question answering and the collaborative development of software. It is also well-recognized that forming the right team in social networks is non-trivial. Although many algorithms have been proposed for resolving this problem, most of them are based on very different criteria, concerns and performance metrics, and their performance has not been empirically compared. In this paper, we first compare and contrast all the state-of-the-art team formation algorithms. Next, we propose a benchmark that enables fair comparison amongst these algorithms. We then implement these algorithms using a common platform and evaluate their performance using several real datasets. We also present our insights arising from the results of the comparison and uncover interesting issues for further research. Our experiments are repeatable, with the code and all the datasets publicly accessible in our website at the following url address: www.cse.ust.hk/~xwangau/TF.html.