Improving Automated Bug Triaging with Specialized Topic Model

Abstract

Bug triaging refers to the process of assigning a bug to the most appropriate developer to fix. It becomes more and more difficult and complicated as the size of software and the number of developers increase. In this paper, we propose a new framework for bug triaging, which maps the words in the bug reports (i.e., the term space) to their corresponding topics (i.e., the topic space). We propose a specialized topic modeling algorithm named multi-feature topic model (MTM) which extends Latent Dirichlet Allocation (LDA) for bug triaging. MTM considers product and component information of bug reports to map the term space to the topic space. Finally, we propose an incremental learning method named TopicMiner which considers the topic distribution of a new bug report to assign an appropriate fixer based on the affinity of the fixer to the topics. We pair TopicMiner with MTM (TopicMiner M T M ). We have evaluated our solution on 5 large bug report datasets including GCC, OpenOffice, Mozilla, Netbeans, and Eclipse containing a total of 227,278 bug reports. We show that TopicMiner M T M can achieve top-1 and top-5 prediction accuracies of 0.4831 -0.6868, and 0.7686 -0.9084, respectively. We also compare TopicMiner M T M with Bugzie, LDA-KL, SVM-LDA, LDA-Activity, and Yang et al.'s approach. The results show that TopicMiner M T M on average improves top-1 and top-5 prediction accuracies of Bugzie by 128.48% and 53.22%, LDA-KL by 262.91% and 105.97%, SVM-LDA by 205.89% and 110.48%, LDA-Activity by 377.60% and 176.32%, and Yang et al.'s approach by 59.88% and 13.70%, respectively.

Improving Bug Triage with Relevant Search

“…However, the "assigned to" fields in many bug reports are set to generic names which do not correspond to real people [19]. In Eclipse, bug reports are assigned to generic names like "JDT-UI-Inbox", "JDT-Text-Inbox", "JDT-Core-Inbox".…”

“…Because these generic names do not represent real developers, we do not recommend them and exclude bug reports whose fixers are among them from the data. Then to reduce noise, bug reports whose fixers appear less than ten times are excluded [19].…”

“…To make our experiments are more like the situation in practice, we adopt the longitudinal data setup in [9] [19]. We perform a 10-round incremental analysis on the two project datasets.…”

“…To make our results comparable, we choose a metric called Recall@K used in many prior studies [5] [19]. Recall@K is the proportion of bugs whose associated developers is ranked in the top k (k = 1, 3, 5) of the returned results.…”

Automated Bug Assignment in Software Maintenance Using Graph Databases

“…One of the main reasons for such processing is found to be the time spent on manual verification of bugs and identification of suitable engineers to fix the bugs [5]. Hence faster identification of suitable engineers for fixing bugs will be a great performance booster for software maintenance [6].…”