文献类型：期刊文献

英文题名：An Empirical Study of Model-Agnostic Interpretation Technique for Just-in-Time Software Defect Prediction

作者：Yang, Xingguang[1,2]; Yu, Huiqun[1,3]; Fan, Guisheng[1]; Huang, Zijie[1]; Yang, Kang[1]; Zhou, Ziyi[1]

机构：[1] Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China; [2] Shanghai Key Laboratory of Computer Software Evaluating and Testing, Shanghai, 201112, China; [3] Shanghai Engineering Research Center of Smart Energy, Shanghai, China

年份：2021

卷号：406 LNICST

起止页码：420

外文期刊名：Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

收录：EI(收录号：20220211454970)

语种：英文

外文关键词：Computer software selection and evaluation - Decision making - Defects - Forecasting - Learning systems - Lime - Open source software - Quality assurance - Software design

摘要：Just-in-time software defect prediction (JIT-SDP) is an effective method of software quality assurance, whose objective is to use machine learning methods to identify defective code changes. However, the existing research only focuses on the predictive power of the JIT-SDP model and ignores the interpretability of the model. The need for the interpretability of the JIT-SDP model mainly comes from two reasons: (1) developers expect to understand the decision-making process of the JIT-SDP model and obtain guidance and insights; (2) the prediction results of the JIT-SDP model will have an impact on the interests of developers. According to privacy protection laws, prediction models need to provide explanations. To this end, we introduced three classifier-agnostic (CA) technologies, LIME, BreakDown, and SHAP for JIT-SDP models, and conducted a large-scale empirical study on six open source projects. The empirical results show that: (1) Different instances have different explanations. On average, the feature ranking difference of two random instances is 3; (2) For a given system, the feature lists and top-1 feature generated by different CA technologies have strong agreement; However, CA technologies have small agreement on the top-3 features in the feature ranking lists. In the actual software development process, we suggest using CA technologies to help developers understand the prediction results of the model. ? 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.