论文标题
软件工程的机器学习：三级研究
Machine Learning for Software Engineering: A Tertiary Study
论文作者
论文摘要
机器学习（ML）技术提高了软件工程（SE）生命周期活动的有效性。我们系统地收集，质量评估，汇总并分类了2009 - 2022年间发表的SE的83个评论，涵盖了6,117项主要研究。最多使用ML的SE区域是软件质量和测试，而以人为中心的区域对于ML来说似乎更具挑战性。我们为SE研究挑战和行动提出了许多ML，包括：对ML进行进一步的经验验证和工业研究；重新考虑不足的SE方法；记录和自动化数据收集和管道过程；重新审查工业从业人员如何分发其专有数据；并实施增量ML方法。
Machine learning (ML) techniques increase the effectiveness of software engineering (SE) lifecycle activities. We systematically collected, quality-assessed, summarized, and categorized 83 reviews in ML for SE published between 2009-2022, covering 6,117 primary studies. The SE areas most tackled with ML are software quality and testing, while human-centered areas appear more challenging for ML. We propose a number of ML for SE research challenges and actions including: conducting further empirical validation and industrial studies on ML; reconsidering deficient SE methods; documenting and automating data collection and pipeline processes; reexamining how industrial practitioners distribute their proprietary data; and implementing incremental ML approaches.
