Boosting crash-inducing change localization with rank-performance-based feature subset selection
Boosting crash-inducing change localization with rank-performance-based feature subset selection
复制标题
通过基于排名性能的特征子集选择来促进导致崩溃的更改本地化
DOI：
10.1007/s10664-020-09802-1
复制
发表时间：
2020-03
影响因子：
4.1
通讯作者：
Baowen Xu
中科院分区：
文献类型：
--
作者：
Zhaoqiang Guo;Yanhui Li;Wanwangying Ma;Yuming Zhou;Hongmin Lu;Lin Chen;Baowen Xu
在给定大量崩溃报告的情况下，如果能够自动定位导致崩溃的软件更改，将有助于开发人员找到并修复相应的缺陷。最近，有人提出了一种称为ChangeLocator的方法，该方法使用10个变化层特征来训练一个基于历史固定崩溃数据的监督模型。据报道，当这十个特征结合在一起时，ChangeLocator在Recall@1、MAP和MRR方面取得了良好的表现。然而，在ChangeLocator中，忽略了特征之间的冗余，这可能会降低定位效果。本文提出了一种改进的基于等级性能的特征选择技术(RFS)的改进方法ChangeRanker，以提高碰撞诱导变更定位的有效性。我们在NetBeans上的实验结果表明，ChangeRanker在召回@1、MRR和MAP方面分别比ChangeLocator提高了35.9%、17.4%和15.3%。此外，与三种流行的特征选择方法相比，RFS能够选择更多的信息特征来提高定位效果。为了评估所提出的扩展的真实泛化能力，我们采用ChangeRanker和ChangeLocator在另外三个数据集上定位引起错误的变化。同样，我们观察到，平均而言，ChangeRanker在Recall@1、MRR和MAP方面分别提高了115.3%、37.6%和41.2%。这表明我们提出的基于排序性能的特征选择方法具有很好的泛化能力。总而言之，我们的工作提供了一种易于使用的方法来提高最先进的崩溃诱导更改本地化方法的性能。
Given a bucket of crash reports, it would be helpful for developers to find and fix the corresponding defects if the crash-inducing software changes can be automatically located. Recently, an approach called ChangeLocator was proposed, which used ten change-level features to train a supervised model based on the data from the historical fixed crashes. It was reported that ChangeLocator achieved a good performance in terms of Recall@1, MAP, and MRR, when all the ten features were combined together. However, in ChangeLocator, the redundancy between features are neglected, which may degrade the localization effectiveness. In this paper, we propose an improved approach ChangeRanker with a rank-performance-based feature selection technology (Rfs) to boost the effectiveness of crash-inducing change localization. Our experimental results on NetBeans show that ChangeRanker can achieve an improvement of 35.9%, 17.4%, and 15.3% over ChangeLocator in terms of Recall@1, MRR, and MAP, respectively. Furthermore, compared with three popular feature selection approaches, Rfs is able to select more informative features to boost localization effectiveness. In order to assess the real generalization capability of the proposed extension, we adapt ChangeRanker and ChangeLocator to locate bug-inducing changes on three additional data sets. Again, we observe that, on average, ChangeRanker achieves an improvement of 115.3%, 37.6%, and 41.2% in terms of Recall@1, MRR, and MAP, respectively. This indicates that our proposed rank-performance-based feature selection method has a good generalization capability. In summary, our work provides an easy-to-use approach to boosting the performance of the state-of-the-art crash-inducing change localization approach.
登录
查看更多内容
影响因子：
5.3
作者：
通讯作者：
--
影响因子：
1.9
作者：
An, Le;Khomh, Foutse;Gueheneuc, Yann-Gael
通讯作者：
Gueheneuc, Yann-Gael
DOI：
10.1109/issre.2016.13
发表时间：
2016-10
期刊：
2016 IEEE 27th International Symposium on Software Reliability Engineering (ISSRE)
影响因子：
--
作者：
Zhou Xu;Jin Liu;Zijiang Yang;G. An;Xiangyang Jia
通讯作者：
Zhou Xu;Jin Liu;Zijiang Yang;G. An;Xiangyang Jia
影响因子：
7.4
作者：
Qinbao Song;Yuchen Guo;M. Shepperd
通讯作者：
Qinbao Song;Yuchen Guo;M. Shepperd
影响因子：
7.4
作者：
Dongsun Kim;Xinming Wang;Sunghun Kim;A. Zeller;S. Cheung;S. Park
通讯作者：
Dongsun Kim;Xinming Wang;Sunghun Kim;A. Zeller;S. Cheung;S. Park