@conference {Anvik:2006:FTB:1134285.1134336, title = {Who should fix this bug?}, booktitle = {Proceedings of the 28th international conference on Software engineering}, series = {ICSE {\textquoteright}06}, year = {2006}, pages = {361{\textendash}370}, publisher = {ACM}, organization = {ACM}, address = {New York, NY, USA}, abstract = {Open source development projects typically support an open bug repository to which both developers and users can report bugs. The reports that appear in this repository must be triaged to determine if the report is one which requires attention and if it is, which developer will be assigned the responsibility of resolving the report. Large open source developments are burdened by the rate at which new bug reports appear in the bug repository. In this paper, we present a semi-automated approach intended to ease one part of this process, the assignment of reports to a developer. Our approach applies a machine learning algorithm to the open bug repository to learn the kinds of reports each developer resolves. When a new report arrives, the classifier produced by the machine learning technique suggests a small number of developers suitable to resolve the report. With this approach, we have reached precision levels of 57\% and 64\% on the Eclipse and Firefox development projects respectively. We have also applied our approach to the gcc open source development with less positive results. We describe the conditions under which the approach is applicable and also report on the lessons we learned about applying machine learning to repositories used in open source development.}, keywords = {bug fixing, bug report, bug report assignment, bug triage, eclipse, Firefox, gcc, issue tracking, machine learning, problem tracking}, isbn = {1-59593-375-1}, doi = {10.1145/1134285.1134336}, url = {http://doi.acm.org/10.1145/1134285.1134336}, author = {Anvik, John and Hiew, Lyndon and Murphy, Gail C.} }