Feature Ranking and Aggregation for Bug Triaging in Open-Source Issue Tracking Systems

The increasing complexity and team-based projects have lead to the rise of various project management tools and techniques. One of the important components of open- source project management is the usage of bug tracking systems. In the last few decades, software projects have experienced an inescapable appearance of bug reports. One of the main challenges in handling these incoming bugs is triaging of bug reports. Bug triaging can be considered as a mechanism for the election of a suitable software developer for a reported bug who will work towards resolving bug in a timely fashion. There exist several semi and fully automated bug triaging techniques in the existing literature. These techniques often consider varied bug parameters for prominent developer selection. Past researchers have concluded different parameters to be possessing prime importance in the optimal developer selection task. However, a common ranking scale depicting the importance among different bug parameters for bug triaging is not available. This paper presents a methodology to rank the non-textual bug parameters using feature ranking and aggregation techniques. The presented methodology has been evaluated on four open-source systems, namely, Mozilla Firefox, Eclipse, GNome and Open Office. From the experimental evaluation, it has been observed that the ranking of bug parameters is consistent among the different open-source projects of Bugzilla repository.