| 摘要: |
| 软件系统的实体演化耦合分析有助于共同变更预测、软件供应链风险识别、代码漏洞溯源、缺陷预测、架构问题定位等分析活动.两个代码实体之间存在演化耦合（evolutionary coupling）是指在软件修订历史中，这对实体倾向于共同变更（共变）.已有的演化耦合分析方法难以准确检测软件维护历史中频繁发生的、有“距离”的共变.为了解决这一问题，提出了基于关联规则挖掘、情节挖掘、潜在语义索引模型相结合的演化耦合分析方法（association rule，MINEPI and LSI based method，AR-MIM），以挖掘有“距离”的共同变更关系.实验收集了58个Python项目、242 074条训练数据、330 660条ground truth的数据集，与已有的4种baseline方法进行了比较，验证了AR-MIM的效果.结果表明：在预测共同变更候选项场景上，AR-MIM的准确性、召回率、F1分数均优于已有方法. |
| 关键词: 提交历史 演化耦合 情节挖掘 潜在语义索引 关联规则挖掘 |
| DOI：10.13328/j.cnki.jos.006853 |
| 分类号: |
| 基金项目:国家重点研发计划（2018YFB1004500）；国家自然科学基金（61902306，62002280，61721002，61833015，62272387）；中央高校基本科研业务费专项资金；中国博士后基金（2020M683507，2019TQ0251，2020M673439）；西安市科协青年人才支持计划（095920201303） |
|
| Evolutionary Coupling Analysis Method of Software Entity Based on Episode Mining |
|
ZHANG Xin-Yu1, JIN Wu-Xia1, LIU Jing-Wen2, FAN Ming2, LIU Ting2
|
|
1.School of Software Engineering, Xi'an Jiaotong University, Xi'an 710049, China;2.School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an 710049, China
|
| Abstract: |
| The entity evolutionary coupling analysis of software systems is helpfulfor analysis activities such as co-change candidate prediction, risk identification of software supply chain, code vulnerability traceability, defect prediction and architecture problem localization. The evolutionary coupling between two entities indicates that these entities tend to be changed together in the software revision history. Existing methods present a low accuracy to detect the frequent "having distance" co-change in the revision history. To address this problem, this study proposes an evolutionary coupling analysis method based on the combination of association rule mining, episode mining and latent semantic indexing (association rule, MINEPI and LSI based method, AR-MIM), which mines co-change relations of "having distance". The experiment verified the effectiveness of AR-MIM by compared with the four baseline methods on the dataset, collecting 58 Python projects, 242 074 pieces of training data, and 330 660 pieces of ground truth. The results show that the precision, recall, and F1 score of AR-MIM are better than those of existing methods in co-change candidate prediction. |
| Key words: commit history evolutionary coupling episode mining latent semantic indexing (LSI) association rule mining |
