Retrieving Rising Stars in Focused Community Question-Answering

Abstract

In Community Question Answering (CQA)‘ forums, there is typically a small fraction of users who provide high-quality posts and earn a very high reputation status from the community. These top contributors are critical to the community since they drive the development of the site and attract traffic from Internet users. Identifying these individuals could be highly valuable, but this is not an easy task. Unlike publication or social networks, most CQA sites lack information regarding peers, friends, or collaborators, which can be an important indicator signaling future success or performance. In this paper, we attempt to perform this analysis by extracting different sets of features to predict future contribution. The experiment covers 376,000 users who remain active in Stack Overflow for at least one year and together contribute more than 21 million posts. One of the highlights of our approach is that we can identify rising stars after short observations. Our approach achieves high accuracy, 85 %, when predicting whether a user will become a top contributor after a few weeks of observation. As a slightly different problem in which we could observe a few posts by a user, our method achieves accuracy higher than 90 %. Our approach provides higher accuracy than baselines methods including a popular time series analysis. Furthermore, our methods are robust to different classifier algorithms. Identifying the rising stars early could help CQA administrators gain an overview of the site’s future and ensure that enough incentive and support is given to potential contributors.