An improved bug localization using structured information retrieval and version history

Locating buggy files is a time consuming and challenging task because defects can deflate from a large variety of sources. So, researchers proposed several automated bug localization techniques where the accuracy can be improved. In this paper, an information retrieval based bug localization technique has been proposed, where buggy files are identified by measuring the similarity between bug report and source code. Besides this, source code structure and frequently changed files are also incorporated to produce a better rank for buggy files. To evaluate the proposed approach, a large-scale experiment on three open source projects, namely SWT, ZXing and Guava has been conducted. The result shows that the proposed approach improves 7% in terms of Mean Reciprocal Rank (MRR) and about 8% for Mean Average Precision (MAP) compared to existing techniques.