基于大数据的开源项目缺陷报告智能预检技术

doi:10.11959/j.issn.2096-0271.2021004

大数据 ›› 2021, Vol. 7 ›› Issue (1): 48-63.doi: 10.11959/j.issn.2096-0271.2021004

• 专题：数据驱动的软件智能化开发 • 上一篇下一篇

基于大数据的开源项目缺陷报告智能预检技术

席圣渠¹^,², 徐锋¹^,², 陈鑫¹^,², 李宣东¹^,²

¹ 南京大学计算机科学与技术系，江苏南京 210023
² 计算机软件新技术国家重点实验室（南京大学），江苏南京 210023

出版日期:2021-01-15 发布日期:2021-01-01
作者简介:席圣渠（1992- ），男，南京大学计算机科学与技术系博士生，主要研究方向为基于深度学习的软件智能开发方法
徐锋（1975- ），男，博士，南京大学计算机科学与技术系教授、博士生导师，主要研究方向为智能化软件可信术
陈鑫（1975- ），男，博士，南京大学计算机科学与技术系副教授，主要研究方向为嵌入式系统、软件建模与分、软件测试与验证
李宣东（1963- ），男，博士，南京大学计算机科学与技术系教授、博士生导师，软件学院院长，主要研究方向为软件建模与分析、软件测试与验证
基金资助:
国家重点研发计划基金资助项目(2016YFB1000800);国家自然科学基金资助项目(61672274);国家自然科学基金资助项目(61702252);江苏省协同创新中心项目

Big-data based intelligent bug triage techniques for open-source projects

Shengqu XI¹^,², Feng XU¹^,², Xin CHEN¹^,², Xuandong LI¹^,²

¹ Department of Computer Science, Nanjing University, Nanjing 210023, China
² State Key Laboratory for Novel Software Technology at Nanjing University, Nanjing 210023, China

Online:2021-01-15 Published:2021-01-01
Supported by:
The National Key Research and Development Program of China(2016YFB1000800);The National Natural Science Foundation of China(61672274);The National Natural Science Foundation of China(61702252);Collaborative Innovation Center of Novel Software Technology and Industrialization of Jiangsu Province

摘要/Abstract

摘要：

缺陷报告预检目标在于确定优先级和修复措施，是保障软件可信的关键环节。然而，在日益普及的开源项目中，由于缺陷数量众多、缺乏组织管理等特性，人工预检难以及时完成，迫切需要基于大数据的自动化、智能化预检技术。结合工业界、学术界对缺陷报告预检的认知，提出了一种智能化缺陷报告预检技术框架，全面系统地归纳了缺陷报告预检中存在的3个关键任务：缺陷优先级分类、缺陷分派、缺陷再分派，并结合开源项目的特点提出了相关技术。实验结果初步验证了上述技术的合理性和有效性。

关键词: 缺陷报告预检, 缺陷优先级, 缺陷分派, 缺陷再分派

Abstract:

Bug triage aims to determine the priority and repair measures and is critical in ensuring software trustability. However, in the increasingly popular open-source projects, due to a large number of defects and lack of organization and management, it is challenging to triage all the bug reports by hand on time, making big-data based, automated and intelligent bug triage urgent. An intelligent bug triage technical framework based on industry and academia’s cognition was proposed, and three key tasks: bug priority classification, bug assignment, and bug reassignment, were identified comprehensively and systematically. Related technologies for the characteristics of open-source projects were proposed. The preliminary experiment results show the reasonableness and effectiveness of the above techniques.

Key words: bug triage, bug prioritization, bug assignment, bug re-assignment

中图分类号:

G434

席圣渠, 徐锋, 陈鑫, 李宣东. 基于大数据的开源项目缺陷报告智能预检技术[J]. 大数据, 2021, 7(1): 48-63.

Shengqu XI, Feng XU, Xin CHEN, Xuandong LI. Big-data based intelligent bug triage techniques for open-source projects[J]. Big Data Research, 2021, 7(1): 48-63.

图/表 8

图1

图2

图3

表1

图4

表2

图5

表3

参考文献 41

[1]	XIE T , ZHANG L , XIAO X ,et al. Cooperative software testing and analysis:advances and challenges[J]. Journal of Computer Science ＆amp; Technology, 2014,29(4): 713-723.
[2]	GUO P J , ZIMMERMANN T , NAGAPPAN N ,et al. Characterizing and predicting which bugs get fixed: an empirical study of Microsoft Windows[C]// The 32nd ACM/IEEE International Conference on Software Engineering. [S.l.:s.n.], 2010: 495-504.
[3]	JEONG G , KIM S , ZIMMERMANN T ,et al. Improving bug triage with bug tossing graphs[C]// The 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering. New York: ACM Press, 2009: 111-120.
[4]	ZOU W , LO D , CHEN Z ,et al. How practitioners perceive automated bug report management techniques[J]. IEEE Transactions on Software Engineering, 2020,46: 836-862.
[5]	ALENEZI M , BANITAAN S . Bug reports prioritization: which features and classifier to use[C]// 2013 12th International Conference on Machine Learning and Applications. Piscataway:IEEE Press, 2013: 112-116.
[6]	SAH R K , KHURSHID S , PERRY D E . Understanding the triaging and fixing processes of long lived bugs[J]. Information and Software Technology, 2015,65(C).
[7]	PODGURSKI A , LEON D , FRANCIS P ,et al. Automated support for classifying software failure reports[C]// The 25th International Conference on Software Engineering. Piscataway: IEEE Press, 2003: 465-475.
[8]	KANWAL J , MAQBOOL O . Bug prioritization to facilitate bug report triage[J]. Bug prioritization to facilitate bug report triage, 2012,27(2): 397-412.
[9]	TIAN Y , LO D , SUN C . Drone: predicting priority of reported bugs by multi-factor analysis[C]// 2013 IEEE International Conference on Software Maintenance. Piscataway: IEEE Press, 2013: 200-209.
[10]	UMER Q , LIU H , SULTAN Y ,et al. Emotion based automated priority prediction for bug reports[J]. IEEE Access, 2018,6: 35743-35752.
[12]	UMER Q , LIU H , ILLAHI I . CNN-based automatic prioritization of bug reports[J]. IEEE Transactions on Reliability, 2019(99): 1-14.
	VALDIVIA-GARCIA H , SHIHAB E ,et al. Characterizing and predicting blocking bugs in open source projects[C]// The 11th Working Conference on Mining Software Repositories. New York: ACM Press, 2014: 72-81.
[13]	JIANG Y , LU P , SU X ,et al. LTRWES: a new framework for security bug report detection[J]. Information and Software Technology, 2020,124: 106314.
[14]	YANG X L , LO D , XIA X ,et al. Highimpact bug report identification with imbalanced learning strategies[J]. Journal of Computer Science and Technology, 2017,32(1): 181-198.
[15]	REN H , LI Y , CHEN L . An empirical study on critical blocking bugs[C]// The 28th International Conference on Program Comprehension. New York: ACM Press, 2020:
[16]	MURPHY G , CUBRANIC D ,et al. Automatic bug triage using text categorization[C]// The 16th International Conference on Software Engineering ＆amp; Knowledge Engineering. [S.l.:s.n.], 2004: 1-6.
[17]	ANVIK J , HIEW L , MURPHY G C ,et al. Who should fix this bug[C]// The 28th International Conference on Software Engineering. New York: ACM Press, 2006: 361-370.
[18]	TAMRAWI A , NGUYEN T T , ALKOFAHI J M ,et al. Fuzzy set and cachebased approach for bug triaging[C]// The 19th ACM SIGSOFT Symposium and the 13th European Conference on Foundations of Software Engineering. New York: ACM Press, 2011: 365-375.
[19]	YANG G , ZHANG T , LEE B . Towards semi-automatic bug triage and severity prediction based on topic model and multifeature of bug reports[C]// IEEE Computer Software ＆amp; Applications Conference. Piscataway: IEEE Press, 2014.
[20]	XIA X , LO D , DING Y ,et al. Improving automated bug triaging with specialized topic model[J]. IEEE Transactions on Software Engineering, 2016,43(3): 272-297.
[21]	LEE S R , HEO M J , LEE C G ,et al. Applying deep learning based automatic bug triager to industrial projects[C]// The 2017 11th Joint Meeting on Foundations of Software Engineering. New York: ACM Press, 2017: 926-931.
[22]	MANI S , SANKARAN A , ARALIKATTE R . Deeptriage: exploring the effectiveness of deep learning for bug triaging[C]// The ACM India Joint International Conference on Data Science and Management of Data. [S.l.:s.n.], 2019: 171-179.
[23]	ALKHAZI B , DISTASI A , ALJEDAANI W ,et al. Learning to rank developers for bug report assignment[J]. Applied Soft Computing, 2020,95: 106667.
[24]	ZHANG T , CHEN J , JIANG H ,et al. Bug report enrichment with application of automated fixer recommendation[C]// IEEE/ACM International Conference on Program Comprehension. Piscataway:IEEE Press, 2017.
[25]	SUN X B , ZHOU C , YANG H ,et al. Developer recommendation for software security bugs[J]. Journal of Software, 2018,29(8): 2294-2305.
[26]	YADAV A , SINGH S K , SURI J S ,et al. Ranking of software developers based on expertise score for bug triaging[J]. Information and Software Technology, 2019,112: 1-17.
[27]	GUO S , ZHANG X , YANG X ,et al. Developer activity motivated bug triaging:via convolutional neural network[J]. Neural Processing Letters, 2020,51(3): 2589-2606.
[28]	BHATTACHARYA P , NEAMTIU I , SHELTON C R . Automated, highlyaccurate, bug assignment using machine learning and tossing graphs[J]. Journal of Systems and Software, 2012,85(10): 2275-2292.
[29]	WU H R , LIU H Y , MA Y T ,et al. Empirical study on developer factors affecting tossing path length of bug reports[J]. IET Software, 2018,12(3): 258-270.
[30]	XIA X , LO D , SHIHAB E ,et al. Automatic, high accuracy prediction of reopened bugs[J]. Automated Software Engineering, 2015,22(1): 75-109.
[31]	MI Q , KEUNG J , HUO Y ,et al. Not all bug reopens are negative: a case study on eclipse bug reports[J]. Information ＆amp;Software Technology, 2018,99: 93-97.
[32]	BLEI D M , NG A Y , JORDAN M I ,et al. Latent dirichlet allocation[J]. Journal of Machine Learning Research, 2012,3(4-5): 993-1022.
[33]	ASUNCION A , WELLING M , SMYTH P ,et al. On smoothing and inference for topic models[J]. arXiv preprint, 2020, arXiv:1205.2662.
[34]	DENTON E , GROSS S , FERGUS R ,et al. Semisupervised learning with context-conditional generative adversarial networks[J]. arXiv preprint, 2016, arXiv:1611.06430.
[35]	SALIMANS T , GOODFELLOW I , ZAREMBA W ,et al. Improved techniques for training gans[C]// Advances in Neural Information Processing Systems. New York: ACM Presss, 2016: 2234-2242.
[36]	SAHA R K , KHURSHID S , PERRY D E ,et al. An empirical study of long lived bugs[C]// 2014 Software Evolution Week-IEEE Conference on Software Maintenance, Reengineering, and Reverse Engineering (CSMR-WCRE). Piscataway:IEEE Press, 2014: 144-153.
[37]	JOHNSON R , ZHANG T . Supervised and semi-supervised text categorization using LSTM for region embeddings[J]. arXiv preprint, 2016, arXiv:1602.02373.
[38]	YANG Z , YANG D , DYER C ,et al. Hierarchical attention networks for document classification[C]// The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [S.l.:s.n.], 2016: 1480-1489.
[39]	CHANG C C , LIN C J . LIBSVM: a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011,2(3).
[40]	SUTSKEVER I , VINYALS O , LE Q V . Sequence to sequence learning with neural networks[C]// Advances in Neural Information Processing Systems. New York: ACM Press, 2014: 3104-3112.
[41]	BAHDANAU D , CHO K , BENGIO Y ,et al. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint, 2014, arXiv:1409.0473.

对比方法	P1		P2		P3		P4		P5
对比方法	精度	召回率	精度	召回率	精度	召回率	精度	召回率	精度	召回率
DRONE	34.51%	32.58%	15.83%	21.68%	86.89%	80.49%	11.98%	16.91%	5.00%	16.28%
BiRNN	38.99%	36.46%	21.31%	23.41%	88.93%	88.45%	13.59%	18.38%	8.47%	17.44%
CPur	39.88%	37.22%	20.54%	22.77%	89.72%	88.57%	12.44%	18.38%	7.94%	18.60%
BrCCGAN	42.65%	41.64%	24.79%	24.77%	86.75%	82.12%	24.32%	26.47%	17.59%	22.09%

实验对象	SVM	Yang	TopicMinerMTM	DeepTriage
Eclipse	28.05%	32.12%	36.89%	41.66%
Netbeans	29.32%	35.29%	42.37%	49.30%
Mozilla	20.43%	26.06%	29.04%	32.32%
Redhat	22.76%	39.83%	45.91%	48.58%

实验对象	SVM	DBRNN+A	CNN Triager	iTriage@1	iTriage@2	iTriage@3
Eclipse	28.06%	28.71%	28.92%	47.86%	54.15%	62.33%
Mozilla	20.43%	20.74%	20.83%	37.31%	42.31%	44.68%
Gentoo	22.76%	24.71%	24.99%	48.58%	56.33%	58.58%

基于大数据的开源项目缺陷报告智能预检技术

Big-data based intelligent bug triage techniques for open-source projects

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 41

相关文章 2

Metrics

推荐阅读 0

[1]	刘烨, 成伟, 李焱, 尹依梦, 孙慧杰. 元宇宙视域下教育社区构建研究[J]. 大数据, 2023, 9(1): 78-86.
[2]	杨琳, 王炜, 诸纪, 王明政. 面向数据共享的教育数据标准体系研究与建设实践[J]. 大数据, 2020, 6(6): 3-13.