Automated,highly-accurate,bug assignment using machine learning and tossing graphs

Empirical studies indicate that automating the bug assignment process has the potential to significantly reduce software evolution effort and costs. Prior work has used machine learning techniques to automate bug assignment but has employed a narrow band of tools which can be ineffective in large, long-lived software projects. To redress this situation, in this paper we employ a comprehensive set of machine learning tools and a probabilistic graph-based model (bug tossing graphs) that lead to highly-accurate predictions, and lay the foundation for the next generation of machine learning-based bug assignment. Our work is the first to examine the impact of multiple machine learning dimensions (classifiers, attributes, and training history) along with bug tossing graphs on prediction accuracy in bug assignment. We validate our approach on Mozilla and Eclipse, covering 856,259 bug reports and 21 cumulative years of development. We demonstrate that our techniques can achieve up to 86.09% prediction accuracy in bug assignment and significantly reduce tossing path lengths. We show that for our data sets the Naïve Bayes classifier coupled with product–component features, tossing graphs and incremental learning performs best. Next, we perform an ablative analysis by unilaterally varying classifiers, features, and learning model to show their relative importance of on bug assignment accuracy. Finally, we propose optimization techniques that achieve high prediction accuracy while reducing training and prediction time.     

基于缺陷相似度与再分配图的软件缺陷分配方法

准确地将缺陷分配给最合适的修复者对大型软件项目的缺陷修复具有重要意义。当前缺陷自动分配技术的研究主要利用历史缺陷报告的描述信息、缺陷关联信息、历史分派信息等,但这些方法都没有将缺陷报告信息充分挖掘。提出在缺陷报告分配时将缺陷历史分派信息和缺陷文本相似信息相结合。首先根据缺陷历史分派信息生成再分配图;然后计算新缺陷报告与历史缺陷报告缺陷的文本相似度,找出相似度最高的前K个缺陷报告所对应的修复者;最后,根据这些修复者在再分配图中的依赖关系生成预测再分配路径。为了验证该方法的有效性,利用Eclipse和Mozilla的缺陷报告集进行实验,实验表明提出的方法在预测的准确度上明显优于其他方法。     

基于Box-Cox转换的集成跨项目软件缺陷预测方法

软件缺陷预测通过预先识别出被测项目内的潜在缺陷程序模块,可以优化测试资源的分配并提高软件产品的质量。论文对跨项目缺陷预测问题展开了深入研究,在源项目实例选择时,考虑了三种不同的实例相似度计算方法,并发现这些方法的缺陷预测结果存在多样性,因此提出了一种基于Box-Cox转换的集成跨项目软件缺陷预测方法BCEL,具体来说,首先基于不同的实例相似度计算方法,从候选集中选出不同的训练集,随后针对这些数据集,进行针对性的Box-Cox转化,并借助特定分类方法构造出不同的基分类器,最后将这三个基分类器进行有效集成。基于实际项目的数据集,验证了BCEL方法的有效性,并深入分析了BCEL方法内的影响因素对缺陷预测性能的影响。     

基于深度自编码网络的软件缺陷预测方法

软件缺陷预测是提升软件质量的有效方法,而软件缺陷预测方法的预测效果与数据集自身的特点有着密切的相关性。针对软件缺陷预测中数据集特征信息冗余、维度过大的问题,结合深度学习对数据特征强大的学习能力,提出了一种基于深度自编码网络的软件缺陷预测方法。该方法首先使用一种基于无监督学习的采样方法对6个开源项目数据集进行采样,解决了数据集中类不平衡问题;然后训练出一个深度自编码网络模型。该模型能对数据集进行特征降维,模型的最后使用了三种分类器进行连接,该模型使用降维后的训练集训练分类器,最后用测试集进行预测。实验结果表明,该方法在维数较大、特征信息冗余的数据集上的预测性能要优于基准的软件缺陷预测模型和基于现有的特征提取方法的软件缺陷预测模型,并且适用于不同分类算法。     

基于深度学习的安全缺陷报告预测方法实证研究

软件安全问题的发生在大多数情况下会造成非常严重的后果，及早发现安全问题，是预防安全事故的关键手段之一.安全缺陷报告预测可以辅助开发人员及早发现被测软件中潜藏的安全缺陷，从而尽早得以修复.然而，由于安全缺陷在实际项目中的数量较少，而且特征复杂（即安全缺陷类型繁多，不同类型安全缺陷特征差异性较大），这使得手工提取特征相对困难，并随后造成传统机器学习分类算法在安全缺陷报告预测性能方面存在一定的瓶颈.针对该问题，提出基于深度学习的安全缺陷报告预测方法，采用深度文本挖掘模型TextCNN和TextRNN构建安全缺陷报告预测模型；针对安全缺陷报告文本特征，使用skip-grams方式构建词嵌入矩阵，并借助注意力机制对TextRNN模型进行优化.所构建的模型在5个不同规模的安全缺陷报告数据集上展开了大规模实证研究，实证结果表明：深度学习模型在80%的实验案例中都要优于传统机器学习分类算法，性能指标F1-score平均可提升0.258，在最好的情况下甚至可以提升0.535.除此之外，针对安全缺陷报告数据集存在的类不均衡问题，对不同采样方法进行了实证研究，并对结果进行了分析.     

基于代价极速学习机的软件缺陷报告分类方法

在所有的软件系统开发过程中,Bug的存在是不可避免的问题.对于软件系统的开发者来说,修复Bug最有利的工具就是Bug报告.但是人工识别Bug报告会给开发人员带来新的负担,因此,自动对Bug报告进行分类是一项很有必要的工作.基于此,提出用基于极速学习机的方法来对Bug报告进行分类.具体而言,主要解决Bug报告自动分类的3个问题：第1个是Bug报告数据集里不同类别的样本数量不平衡问题;第2个是Bug报告数据集里被标注的样本不充足问题;第3个是Bug报告数据集总体样本量不充足问题.为了解决这3个问题,分别引入了基于代价的有监督分类方法、基于模糊度的半监督学习方法以及样本迁移方法.通过在多个Bug报告数据集上进行实验,验证了这些方法的可行性和有效性.     

Automated classification of software issue reports using machine learning techniques: an empirical study

Software developers, testers and customers routinely submit issue reports to software issue trackers to record the problems they face in using a software. The issues are then directed to appropriate experts for analysis and fixing. However, submitters often misclassify an improvement request as a bug and vice versa. This costs valuable developer time. Hence automated classification of the submitted reports would be of great practical utility. In this paper, we analyze how machine learning techniques may be used to perform this task. We apply different classification algorithms, namely naive Bayes, linear discriminant analysis, k-nearest neighbors, support vector machine (SVM) with various kernels, decision tree and random forest separately to classify the reports from three open-source projects. We evaluate their performance in terms of F-measure, average accuracy and weighted average F-measure. Our experiments show that random forests perform best, while SVM with certain kernels also achieve high performance.     

An empirical study of factors affecting cross-project aging-related bug prediction with TLAP

Software aging is a phenomenon in which long-running software systems show an increasing failure rate and/or progressive performance degradation. Due to their nature, Aging-Related Bugs (ARBs) are hard to discover during software testing and are also challenging to reproduce. Therefore, automatically predicting ARBs before software release can help developers reduce ARB impact or avoid ARBs. Many bug prediction approaches have been proposed, and most of them show effectiveness in within-project prediction settings. However, due to the low presence and reproducing difficulty of ARBs, it is usually hard to collect sufficient training data to build an accurate prediction model. A recent work proposed a method named Transfer Learning based Aging-related bug Prediction (TLAP) for performing cross-project ARB prediction. Although this method considerably improves cross-project ARB prediction performance, it has been observed that its prediction result is affected by several key factors, such as the normalization methods, kernel functions, and machine learning classifiers. Therefore, this paper presents the first empirical study to examine the impact of these factors on the effectiveness of cross-project ARB prediction in terms of single-factor pattern, bigram pattern, and triplet pattern and validates the results with the Scott-Knott test technique. We find that kernel functions and classifiers are key factors affecting the effectiveness of cross-project ARB prediction, while normalization methods do not show statistical influence. In addition, the order of values in three single-factor patterns is maintained in three bigram patterns and one triplet pattern to a large extent. Similarly, the order of values in the three bigram patterns is also maintained in the triplet pattern.

     

Bug Triaging Based on Tossing Sequence Modeling

Bug triaging, which routes the bug reports to potential fixers, is an integral step in software development and maintenance. To make bug triaging more efficient, many researchers propose to adopt machine learning and information retrieval techniques to identify some suitable fixers for a given bug report. However, none of the existing proposals simultaneously take into account the following three aspects that matter for the efficiency of bug triaging:1) the textual content in the bug reports, 2) the metadata in the bug reports, and 3) the tossing sequence of the bug reports. To simultaneously make use of the above three aspects, we propose iTriage which first adopts a sequence-to-sequence model to jointly learn the features of textual content and tossing sequence, and then uses a classification model to integrate the features from textual content, metadata, and tossing sequence. Evaluation results on three different open-source projects show that the proposed approach has significantly improved the accuracy of bug triaging compared with the state-of-the-art approaches.     

A survey on bug prioritization

Daily large number of bug reports are received in large open and close source bug tracking systems. Dealing with these reports manually utilizes time and resources which leads to delaying the resolution of important bugs. As an important process in software maintenance, bug triaging process carefully analyze these bug reports to determine, for example, whether the bugs are duplicate or unique, important or unimportant, and who will resolve them. Assigning bug reports based on their priority or importance may play an important role in enhancing the bug triaging process. The accurate and timely prioritization and hence resolution of these bug reports not only improves the quality of software maintenance task but also provides the basis to keep particular software alive. In the past decade, various studies have been conducted to prioritize bug reports using data mining techniques like classification, information retrieval and clustering that can overcome incorrect prioritization. Due to their popularity and importance, we survey the automated bug prioritization processes in a systematic way. In particular, this paper gives a small theoretical study for bug reports to motivate the necessity for work on bug prioritization. The existing work on bug prioritization and some possible problems in working with bug prioritization are summarized.     

一种半监督集成跨项目软件缺陷预测方法

软件缺陷预测方法可以在项目的开发初期,通过预先识别出所有可能含有缺陷的软件模块来优化测试资源的分配。早期的缺陷预测研究大多集中于同项目缺陷预测,但同项目缺陷预测需要充足的历史数据,而在实际应用中可能需要预测的项目的历史数据较为稀缺,或这个项目是一个全新项目。因此跨项目缺陷预测问题成为当前软件缺陷预测领域内的一个研究热点,其研究挑战在于源项目与目标项目数据集间存在的分布差异性以及数据集内存在的类不平衡问题。受到基于搜索的软件工程思想的启发,论文提出了一种基于搜索的半监督集成跨项目软件缺陷预测方法S³EL。该方法首先通过调整训练集中各类数据的分布比例,构建出多个朴素贝叶斯基分类器,随后利用具有全局搜索能力的遗传算法,基于少量已标记目标实例对上述基分类器进行集成,并构建出最终的缺陷预测模型。在Promise数据集及AEEEM数据集上和多个经典的跨项目缺陷预测方法（Burak过滤法、Peters过滤法、TCA+、CODEP及HYDRA）进行了对比。以F1值作为评测指标,结果表明在大部分情况下,S³EL方法可以取得最好的预测性能。     

KSAP: An approach to bug report assignment using KNN search and heterogeneous proximity

ContextBug report assignment, namely, to assign new bug reports to developers for timely and effective bug resolution, is crucial for software quality assurance. However, with the increasing size of software system, it is difficult to assign bugs to appropriate developers for bug managers.ObjectiveThis paper propose an approach, called KSAP (K-nearest-neighbor search and heterogeneous proximity), to improve automatic bug report assignment by using historical bug reports and heterogeneous network of bug repository.MethodWhen a new bug report was submitted to the bug repository, KSAP assigns developers for the bug report by using a two-phase procedure. The first phase is to search historically-resolved similar bug reports to the new bug report by K-nearest-neighbor (KNN) method. The second phase is to rank the developers who contributed to those similar bug reports by heterogeneous proximity.ResultsWe collected bug repositories of Mozilla, Eclipse, Apache Ant and Apache Tomcat6 projects to investigate the performance of the proposed KSAP approach. Experimental results demonstrate that KSAP can improve the recall of bug report assignment between 7.5–32.25% in comparison with the state of art techniques. When there is only a small number of developer collaborations on common bug reports, KSAP has shown its excellence over other sate of art techniques. When we tune the parameters of the number of historically-resolved similar bug reports (K) and the number of developers (Q) for recommendation, KSAP keeps its superiority steadily.ConclusionThis is the first paper to demonstrate how to automatically build heterogeneous network of a bug repository and extract meta-paths of developer collaborations from the heterogeneous network for bug report assignment.     

Multiple kernel ensemble learning for software defect prediction

Software defect prediction aims to predict the defect proneness of new software modules with the historical defect data so as to improve the quality of a software system. Software historical defect data has a complicated structure and a marked characteristic of class-imbalance; how to fully analyze and utilize the existing historical defect data and build more precise and effective classifiers has attracted considerable researchers’ interest from both academia and industry. Multiple kernel learning and ensemble learning are effective techniques in the field of machine learning. Multiple kernel learning can map the historical defect data to a higher-dimensional feature space and make them express better, and ensemble learning can use a series of weak classifiers to reduce the bias generated by the majority class and obtain better predictive performance. In this paper, we propose to use the multiple kernel learning to predict software defect. By using the characteristics of the metrics mined from the open source software, we get a multiple kernel classifier through ensemble learning method, which has the advantages of both multiple kernel learning and ensemble learning. We thus propose a multiple kernel ensemble learning (MKEL) approach for software defect classification and prediction. Considering the cost of risk in software defect prediction, we design a new sample weight vector updating strategy to reduce the cost of risk caused by misclassifying defective modules as non-defective ones. We employ the widely used NASA MDP datasets as test data to evaluate the performance of all compared methods; experimental results show that MKEL outperforms several representative state-of-the-art defect prediction methods.     

融合文本分布式表示的重复缺陷报告检测

重复缺陷报告检测能够避免对描述同一缺陷的多份报告进行重复的任务分派和修复,可降低软件维护成本。为了进一步提高检测的准确率,提出一种融合文本分布式表示的重复缺陷报告检测方法。首先,基于大规模缺陷报告数据库训练Doc2Vec模型并抽取缺陷报告的分布式表示,将不同长度的缺陷报告编码为统一长度的稠密向量。接着,通过比较这些向量来计算不同缺陷报告的相似程度,将其作为一种新特征与重复缺陷报告检测过程常用的其它特征进行融合,并利用机器学习算法训练二元分类模型。在公开的Bugzilla重复缺陷报告数据集上的实验结果表明,相比于代表性方法D_TS,本文方法的F1值平均提升了2%,说明了新特征的有效性。     

一种基于文本分类和评分机制的软件缺陷分配方法

开源软件项目的缺陷管理和修复是保障软件质量及软件开发效率的重要手段,而提高软件缺陷分配的效率是其中亟需解决的一个关键问题。文中提出了一种基于文本分类和评分机制的开发者预测方法,其核心思想是综合考虑基于机器学习的文本分类和基于软件缺陷从属特征的评分机制来构建预测模型。针对大型开源软件项目Eclipse和Mozilla的十万级已修复软件缺陷的实验表明,在“十折”增量验证模式下,所提方法的最好平均准确率分别达到了78.39%和64.94%,比基准方法(机器学习分类+再分配图)的最高平均准确率分别提升了17.34%和10.82%,从而验证了其有效性。     

Feature transfer learning by reinforcement learning for detecting software defect

Software defects, produced inevitably in software projects, seriously affect the efficiency of software testing and maintenance. An appealing solution is the software defect prediction (SDP) that has achieved good performance in many software projects. However, the difference between features and the difference of the same feature between training data and test data may degrade defect prediction performance if such differences violate the model's assumption. To address this issue, we propose a SDP method based on feature transfer learning (FTL), which performs a transformation sequence for each feature in order to map the original features to another feature space. Specifically, FTL first uses the reinforcement learning scheme that automatically learns a strategy for transferring the potential feature knowledge from the training data. Then, we use the learned feature knowledge to inspire the transformation of the test data. The classifier is trained by the transformed training data and predicts defects for transformed test data. We evaluate the validity of FTL on 43 projects from PROMISE and NASA MDP using three classifiers, logistic regression, random forest, and Naive Bayes (NB). Experimental results indicate that FTL is better than the original classifiers and has the best performance on the NB classifier. For PROMISE, after using FTL, the average results of F1-score, AUC, MCC are 0.601, 0.757, and 0.350 respectively, which are 24.9%, 2.6%, and 16.7% higher than the original NB classifier results. The number of projects with improved performance accounts for 83.87%, 83.87%, and 64.52%. Similarly, FTL performs well on NASA MDP. Besides, compared with four feature engineering (FE) methods, FTL achieves an excellent improvement on most projects and the average performance is also better than or close to the FE methods.     

Bug Prioritization to Facilitate Bug Report Triage

The large number of new bug reports received in bug repositories of software systems makes their management a challenging task.Handling these reports manually is time consuming,and often results in delaying the resolution of important bugs.To address this issue,a recommender may be developed which automatically prioritizes the new bug reports.In this paper,we propose and evaluate a classification based approach to build such a recommender.We use the Na¨ ve Bayes and Support Vector Machine (SVM) classifiers,and present a comparison to evaluate which classifier performs better in terms of accuracy.Since a bug report contains both categorical and text features,another evaluation we perform is to determine the combination of features that better determines the priority of a bug.To evaluate the bug priority recommender,we use precision and recall measures and also propose two new measures,Nearest False Negatives (NFN) and Nearest False Positives (NFP),which provide insight into the results produced by precision and recall.Our findings are that the results of SVM are better than the Na¨ ve Bayes algorithm for text features,whereas for categorical features,Na¨ ve Bayes performance is better than SVM.The highest accuracy is achieved with SVM when categorical and text features are combined for training.     

Non‐negative sparse‐based SemiBoost for software defect prediction

Software defect prediction is an important decision support activity in software quality assurance. The limitation of the labelled modules usually makes the prediction difficult, and the class‐imbalance characteristic of software defect data leads to negative influence on decision of classifiers. Semi‐supervised learning can build high‐performance classifiers by using large amount of unlabelled modules together with the labelled modules. Ensemble learning achieves a better prediction capability for class‐imbalance data by using a series of weak classifiers to reduce the bias generated by the majority class. In this paper, we propose a new semi‐supervised software defect prediction approach, non‐negative sparse‐based SemiBoost learning. The approach is capable of exploiting both labelled and unlabelled data and is formulated in a boosting framework. In order to enhance the prediction ability, we design a flexible non‐negative sparse similarity matrix, which can fully exploit the similarity of historical data by incorporating the non‐negativity constraint into sparse learning for better learning the latent clustering relationship among software modules. The widely used datasets from NASA projects are employed as test data to evaluate the performance of all compared methods. Experimental results show that non‐negative sparse‐based SemiBoost learning outperforms several representative state‐of‐the‐art semi‐supervised software defect prediction methods. Copyright © 2016 John Wiley & Sons, Ltd.     

融合信息检索和深度模型特征的软件缺陷定位方法

构建自动化的缺陷定位方法能够加快程序员利用缺陷报告定位到复杂软件系统缺陷代码的过程.早期相关研究人员将缺陷定位视为检索任务,通过分析缺陷报告和相关代码构造缺陷特征,并结合信息检索的方法实现缺陷定位.随着深度学习的发展,利用深度模型特征的缺陷定位方法也取得了一定效果.然而,由于深度模型训练的时间成本和耗费资源相对较高,现有基于深度模型的缺陷定位研究方法存在实验搜索空间和真实情况不符的情况.这些研究方法在测试时并没有将项目下的所有代码作为搜索空间,而仅仅搜索了与已有缺陷相关的代码, 例如DNNLOC方法,DeepLocator方法,DreamLoc方法.这种做法和现实中程序员进行缺陷定位的搜索场景是不一致的.致力于模拟缺陷定位的真实场景,本文提出了一种融合信息检索和深度模型特征的TosLoc方法进行缺陷定位.TosLoc方法首先通过信息检索的方式检索真实项目的所有源代码,确保已有特征的充分利用;再利用深度模型挖掘源代码和缺陷报告的语义,获取最终定位结果.通过两阶段的检索,TosLoc方法能够对单个项目的所有代码实现快速缺陷定位.通过在4个常用的真实Java项目上进行实验,本文提出的TosLoc方法能在检索速度和准确性上超越已有基准方法.和最优基准方法DreamLoc相比,TosLoc方法在消耗DreamLoc方法35%的检索时间下,平均MRR值比DreamLoc方法提高了2.5%,平均MAP值提高了6.0%.     

High-Impact Bug Report Identification with Imbalanced Learning Strategies

In practice, some bugs have more impact than others and thus deserve more immediate attention. Due to tight schedule and limited human resources, developers may not have enough time to inspect all bugs. Thus, they often concentrate on bugs that are highly impactful. In the literature, high-impact bugs are used to refer to the bugs which appear at unexpected time or locations and bring more unexpected effects (i.e., surprise bugs), or break pre-existing functionalities and destroy the user experience (i.e., breakage bugs). Unfortunately, identifying high-impact bugs from thousands of bug reports in a bug tracking system is not an easy feat. Thus, an automated technique that can identify high-impact bug reports can help developers to be aware of them early, rectify them quickly, and minimize the damages they cause. Considering that only a small proportion of bugs are high-impact bugs, the identification of high-impact bug reports is a difficult task. In this paper, we propose an approach to identify high-impact bug reports by leveraging imbalanced learning strategies. We investigate the effectiveness of various variants, each of which combines one particular imbalanced learning strategy and one particular classification algorithm. In particular, we choose four widely used strategies for dealing with imbalanced data and four state-of-the-art text classification algorithms to conduct experiments on four datasets from four different open source projects. We mainly perform an analytical study on two types of high-impact bugs, i.e., surprise bugs and breakage bugs. The results show that different variants have different performances, and the best performing variants SMOTE (synthetic minority over-sampling technique) + KNN (K-nearest neighbours) for surprise bug identification and RUS (random under-sampling) + NB (naive Bayes) for breakage bug identification outperform the F1-scores of the two state-of-the-art approaches by Thung et al. and Garcia and Shihab.