DR_PSF: Enhancing Developer Recommendation by Leveraging Personalized Source-Code Files

Given a new issue request, suitable developers should be arranged to implement it. Technologies such as developer recommendation have been proposed to tackle this issue. These techniques tend to recommend experienced developers, i.e., the more experienced the developer is, the more possible he/she is recommended. However, if the experienced developers are hectic, the junior developers may be employed to finish the incoming issue. But they may have difficulty in finishing these tasks for lack of developing experience. In this paper, we propose a novel approach, DR_PSF (Developer Recommendation with Personalized Source-code Files), to enhance developer recommendation by leveraging personalized source-code files. DR_PSF uses the collaborative topic modeling (CTM) technique to analyze developer expertise and triage some personalized files for the recommended developers. An empirical study is conducted, and the results show that DR_PSF can effectively recommend useful personalized source-code files for them to refer when they implement the incoming issue.