BugRadar: Bug localization by knowledge graph link prediction
BugRadar: Bug localization by knowledge graph link prediction
复制标题
DOI：
10.1016/j.infsof.2023.107274
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Xianni Xiao;Renjie Xiao;Qing Li;Jianhui Lv;Shunyan Cui;Qixu Liu
中科院分区：
文献类型：
--
作者：
Xianni Xiao;Renjie Xiao;Qing Li;Jianhui Lv;Shunyan Cui;Qixu Liu
内容：基于信息检索的错误定位（IRBL）旨在设计一个自动化系统，根据错误报告找到错误文件，从而减少程序员修复错误的时间消耗。近几年来，人们对红外线技术进行了广泛的研究。然而，这些方法不能充分利用缺陷报告和源文件中的结构信息。目的：提出一种新的缺陷检测方案BugRadar。它结合了bug报告和源文件中的文本特征和结构特征，用于bug本地化。方法：提出了一种基于结构特征的知识图TriGraph，并应用双曲注意力嵌入算法得到链接预测得分。对于文本特征，本文提出了部分文本相似度，改进了传统的文本相似度和方法级文本相似度。我们还提出了Word协同过滤分数，它利用历史错误报告，更多地关注重要术语。最后，我们计算出最终的可疑分数的基础上的结构特征，文本特征，并从错误修复history.Results的修复时间信息：我们将我们的计划应用于四个项目（Tomcat，SWT，JDT，和Birt）在一个流行的数据集，并得到了令人满意的结果。BugRadar在四个项目中的三个项目上获得了比其他最先进的方法更好的结果。它实现了8.8%，在SWT和9.8%，在JDT的平均平均精度相比，以前最好的计划KGBugstrike和11.4%，Birt相比Adaptive Regression.Conclusions：BugRadar可以实现批准的性能在大规模的项目与足够的历史错误报告。验证了知识图能够表示缺陷定位的结构特征。新的部分文本相似度和词协同过滤分数都是有效的改进使用文本特征。
Context: Information Retrieval-based Bug Localization (IRBL) aims to design automatic systems that find buggy files according to bug reports, which can reduce the time consumption to fix bugs for programmers. There has been extensive research on IRBL techniques in recent years. However, these methods cannot make full use of the structure information in bug reports and source files.Objective: In this paper, we propose a novel scheme BugRadar. It combines text features and structure features from bug reports and source files for bug localization. Especially, BugRadar leverages a knowledge graph to make use of structure features.Method: We originally propose a knowledge graph named TriGraph based on structure features and apply hyperbolic attention embedding to get the link prediction scores. For text features, we propose Partial Text Similarity which improves traditional Text Similarity and Method Level Text Similarity. We also propose Word Collaborative Filtering Score which leverages historical bug reports with more attention on important terms. Finally, we calculate the final suspicious scores based on the structure features, text features, and fixing time information from bug fixing history with a neural network.Results: We apply our scheme to four projects (Tomcat, SWT, JDT, and Birt) in a popular dataset and get approving results. BugRadar gets better results than other state-of-the-art methods on three projects out of the four. It achieves a relative improvement of 8.8% in SWT and 9.8% in JDT for Mean Average Precision compared to the previous best scheme KGBugLocator and 11.4% in Birt compared to Adaptive Regression.Conclusions: BugRadar can achieve approving performance on large-scale projects with enough historical bug reports. It verifies that knowledge graphs are capable of representing the structure features for bug localization. The novel Partial Text Similarity and Word Collaborative Filtering Score are both effective improvements for using text features.