Automatic bug triage using text categorization

Bug triage, deciding what to do with an incoming bug report, is taking up increasing amount of developer resources in large open-source projects. In this paper, we propose to apply machine learning techniques to assist in bug triage by using text categorization to predict the developer that should work on the bug based on the bug’s description. We demonstrate our approach on a collection of 15,859 bug reports from a large open-source project. Our evaluation shows that our prototype, using supervised Bayesian learning, can correctly predict 30% of the report assignments to developers.

• Type: Conference
• Year: 2004
• Where: SEKE
• Authors: Davor Cubranic, Gail C. Murphy
• Keywords: Bug Reports, Bug Triage, Large Open-source Project, SEKE 2004