TY  - RPRT
ID  - SisLab3724
UR  - https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3724/
A1  - Le, Duc-Trong
Y1  - 2019/10/30/
N2  - Constructing and maintaining open source projects is not an easy work. Developers usually need to tackle a lot of bugs reported by users. The first step of the fixing progress is to find all relevant files respect to given reports. This step takes time and human resources. Motivating from this context, various learning-to-rank models were proposed in order to automatically rank files and generate suggestions for developers. The actual related files are expected to be appeared in high positions of the ranking. In the scope of this paper, a mean reciprocal rank optimization approach is investigated for the learning-to-rank relevant files for bug re- ports task. Given a bug report, the ranking of a source file is approximated by a function aggregating features which represent their relationship. The weights of these features are learned previously to maximize the mean reciprocal rank of known relevant files on training bug reports. In the ex- perimental section, the introduced model is evaluated on three Java open source projects namely Tomcat, AspectJ and SWT. The three different versions of the model are also explored and compared to a recent state-of-the-art method in recommending related files for bug reports.
PB  - Springer
M1  - technical_report
TI  - Finding Relevant Files for Bug Reports
Based on Mean Reciprocal Rank Maximization Approach
AV  - public
EP  - 7
ER  -