Faceted Bug Report Search with Topic Model

Abstract

During bug reporting, The same bugs could be repeatedly reported. As a result, extra time could be spent on bug triaging and fixing. In order to reduce redundant effort, it is important to provide bug reporters with the ability to search for previously reported bugs efficiently and accurately. The existing bug tracking systems are using relatively simple ranking functions, which often produce unsatisfactory results. In this paper, we apply Ranking SVM, a Learning to Rank technique to construct a ranking model for accurate bug report search. Based on the search results, a topic model is used to cluster the bug reports into multiple facets. Each facet contains similar bug reports of the same topic. Users and testers can locate relevant bugs more efficiently through a simple query. We perform evaluations on more than 16,340 Eclipse and Mozilla bug reports. The evaluation results show that the proposed approach can achieve better search results than the existing search functions.