The number of bug reports in complex software increases dramatically. Nowbugs are triaged manually, bug triage or assignment is a labor-intensive andtime-consuming task. Without knowledge about the structure of the software,testers often specify the component of a new bug wrongly. Meanwhile, it isdifficult for triagers to determine the component of the bug only by itsdescription. We dig out the components of 28,829 bugs in Eclipse bug projecthave been specified wrongly and modified at least once. It results in thesebugs have to be reassigned and delays the process of bug fixing. The averagetime of fixing wrongly-specified bugs is longer than that ofcorrectly-specified ones. In order to solve the problem automatically, we usehistorical fixed bug reports as training corpus and build classifiers based onsupport vector machines and Na\"ive Bayes to predict the component of a newbug. The best prediction accuracy reaches up to 81.21% on our validation corpusof Eclipse project. Averagely our predictive model can save about 54.3 days fortriagers and developers to repair a bug. Keywords: bug reports; bug triage;text classification; predictive model
展开▼
