Managing Open Bug Repositories through Bug Report Prioritization Using SVMs

Abstract

Managing the incoming deluge of new bug reports received in bug repository of a large open source project is a challenging task. Handling these reports manually by developers, consume time and resources which results in delaying the resolution of crucial (important) bugs which need to be identified and resolved earlier to prevent major losses in a software project. In this paper, we present a machine learning approach to develop a bug priority recommender which automatically assigns an appropriate priority level to newly arrived bugs, so that they are resolved in order of importance and an important bug is not left untreated for a long time. Our approach is based on the classification technique, for which we use Support Vector Machines. Experimental evaluation of our recommender using precision and recall measures reveals the feasibility of our approach for automatic bug priority assignment.