Predicting the Severity of Bug Reports using Classification Algorithms

Bug triaging is the process of prioritizing the bug reports based on the severity and is driven by the business needs and available resources. Majority times, only few of the reported bugs are selected to be fixed. The selected bugs are prioritized (ordered) based on their severity (e.g. the bug inhibits an important feature of the product, the bug affects a large number of users) and then fixed according to their priority. If the severity is assigned incorrectly then time and resources may be wasted to fix that bug. Hence there is a need for new techniques to avoid this misuse of resources. In this paper, bagging ensemble method is used for predicting the severity of bug reports. Also, bagging ensemble method is compared with C4.5 classifier. The results have shown that bagging ensemble method gives better accuracy compared to C4.5 general classifier on the given dataset.