Influence of Structured Information in Bug Report Descriptions on IR-based Bug Localization

Over the years, researcher proposed multiple information retrieval (IR) based bug localization techniques. The foundation of the approaches relies on textual similarity of the bug report description and the source code files. The basic assumption is that these descriptions are well suited to query the code base. However, often bug reports contain structured information such as stack traces and source code next to natural language, which might interfere with the initial belief. In this paper, we systematically analyze the influence of structured information on IR-based techniques. Therefore a study on 7,334 bug reports, out of which more than 30% contain structured information, was conducted. Our results show, that stack traces tend to negatively affect IR-based bug localization performance and require special handling.