arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2507.04422cs.SEcs.AI
收藏

学习软件缺陷报告:一项系统文献综述

Learning Software Bug Reports: A Systematic Literature Review

University of Electronic Science and Technology of China(电子科技大学);University of Leeds(利兹大学);Loughborough University(洛桑大学);IDEAS Lab, University of Birmingham(伯明翰大学IDEAS实验室);Institute for Clarity in Documentation(文档清晰研究所);Inria Paris-Rocquencourt(巴黎-勒克鲁瓦研究所);Rajiv Gandhi University(拉贾·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕勒研究实验室)

Guoming Long, Jingzhi Gong, Hui Fang, Tao Chen

AI总结:

本文通过系统综述204篇论文,总结了机器学习在软件缺陷报告分析中的常用模型、特征表示、预处理方法、评估任务与指标,并指出统计检验不足及未来研究方向。

摘要:

人工智能尤其是机器学习(ML)的最新进展,已经显著影响了软件工程研究,包括缺陷报告分析。ML旨在自动化地从缺陷报告中理解、提取和关联信息。尽管其重要性日益增长,该领域仍缺乏全面的综述。本文提出了一项系统文献综述,覆盖1,825篇论文,并选取其中204篇进行详细分析。我们得出七项关键发现:1)CNN、LSTM和$k$NN被广泛用于缺陷报告分析,而BERT等先进模型因其复杂性而未得到充分利用。2)Word2Vec和TF-IDF在特征表示中较为流行,深度学习方法的使用呈上升趋势。3)停用词移除是最常见的预处理方法,2020年后结构化方法逐渐增多。4)Eclipse和Mozilla是最常被评估的软件项目。5)缺陷分类是最常见的任务,其次是缺陷定位和严重程度预测。6)对非功能缺陷和性能缺陷等特定缺陷的关注日益增加。7)常用评估指标为F1-score、Recall、Precision和Accuracy,模型评估中更倾向于使用$k$折交叉验证。8)许多研究缺乏稳健的统计检验。我们还确定了六个有前景的未来研究方向,以期为从业者提供有用的见解。

英文摘要:

The recent advancement of artificial intelligence, especially machine learning (ML), has significantly impacted software engineering research, including bug report analysis. ML aims to automate the understanding, extraction, and correlation of information from bug reports. Despite its growing importance, there has been no comprehensive review in this area. In this paper, we present a systematic literature review covering 1,825 papers, selecting 204 for detailed analysis. We derive seven key findings: 1) Extensive use of CNN, LSTM, and $k$NN for bug report analysis, with advanced models like BERT underutilized due to their complexity. 2) Word2Vec and TF-IDF are popular for feature representation, with a rise in deep learning approaches. 3) Stop word removal is the most common preprocessing, with structural methods rising after 2020. 4) Eclipse and Mozilla are the most frequently evaluated software projects. 5) Bug categorization is the most common task, followed by bug localization and severity prediction. 6) There is increasing attention on specific bugs like non-functional and performance bugs. 7) Common evaluation metrics are F1-score, Recall, Precision, and Accuracy, with $k$-fold cross-validation preferred for model evaluation. 8) Many studies lack robust statistical tests. We also identify six promising future research directions to provide useful insights for practitioners.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑