Rank SVM Based Tracking and Mapping Bug Reports to Relevant Files
Abstract: Once the bug occurred, it is a difficult process to localize the bug. It is taking the long time for placing the bug. So the tedious process of placing the bugs taking more time. Sometimes this time taken is more than fixing the bugs. A tool for ranking all the source files of a project with respect to how likely to contain the cause of the bug world enable developers to narrow down their search and potentially could lead to a substantial increase in productivity. Adaptive Rank SVM approach that leverages domain knowledge through functional decompositions of source code files into methods, API descriptions of library components used in the code, the bug-fixing history, and the code changes history. Given a bug report, the ranking score of each source file is computed as a weighted combination of an array of features encoding domain knowledge, where the weights are trained automatically on previously solved bug reports using Learning-to-rank Technique.
Keywords: Ranking Model, Filtering, Pairwise approach
How to Cite?: Dr. S. Preetha, N. Gangarajam, "Rank SVM Based Tracking and Mapping Bug Reports to Relevant Files", Volume 5 Issue 11, November 2016, International Journal of Science and Research (IJSR), Pages: 914-921, https://www.ijsr.net/getabstract.php?paperid=ART20162935, DOI: https://dx.doi.org/10.21275/ART20162935