Automated Classification of Unstructured Bilingual Software Bug Reports: An Industrial Case Study Research

Software bug report classification is a critical process to understand the nature, implications, and causes of software failures. Furthermore, classification enables a fast and appropriate reaction to software bugs. However, for large-scale projects, one must deal with a broad set of bugs from multiple types. In this context, manually classifying bugs becomes cumbersome and time-consuming. Although several studies have addressed automated bug classification using machine learning techniques, they have mainly focused on academic case studies, open-source software, and unilingual text input. This paper presents our automated bug classification approach applied and validated in an industrial case study. In contrast to earlier studies, our study is applied to a commercial software system based on unstructured bilingual bug reports written in English and Turkish. The presented approach adopts and integrates machine learning (ML), text mining, and natural language processing (NLP) techniques to support the classification of software bugs. The approach has been applied within an industrial case study. Compared to manual classification, our results show that bug classification can be automated and even performs better than manual bug classification. Our study shows that the presented approach and the corresponding tools effectively reduce the manual classification time and effort.

Automatic dependent bug reports assembly for bug tracking systems by threshold-based similarity

<p>Bug reports contain essential information for fixing problems that occur in software. Many studies have proposed methods for automatic analysis of bug reports. One such task could affect the completion of software bug fixing, known as “bug dependency”. Although this problem was mentioned by many researches, most of them discussed about the related bugs but not really dealt with dependency issue in bug reports. One possible solution used for addressing this issue is to assemble all relevant/dependent bug reports together before analysis of the next processing stages. This study presents a method of assembling dependent bug reports. The main mechanism is called “threshold-based similarity analysis”, and the three similarity techniques of cosine similarity (CS) multi aspect TF (MATF), and BM25 are compared with feedback, precision and likelihood value. As the BM25 with the threshold as 0.5 gives the best results, it was used to compare with the state of the art method. The results show that our method increases precision and likelihood values by 12% and 12.4% respectively. Therefore, our results can be used to encourage developers to recognize all dependent bugs in the same problem domain.</p>

Severity Prediction for Bug Reports Using Multi-Aspect Features: A Deep Learning Approach

The severity of software bug reports plays an important role in maintaining software quality. Many approaches have been proposed to predict the severity of bug reports using textual information. In this research, we propose a deep learning framework called MASP that uses convolutional neural networks (CNN) and the content-aspect, sentiment-aspect, quality-aspect, and reporter-aspect features of bug reports to improve prediction performance. We have performed experiments on datasets collected from Eclipse and Mozilla. The results show that the MASP model outperforms the state-of-the-art CNN model in terms of average Accuracy, Precision, Recall, F1-measure, and the Matthews Correlation Coefficient (MCC) by 1.83%, 0.46%, 3.23%, 1.72%, and 6.61%, respectively.

Review on Structural Software Testing Coverage Approaches

Testing is broadly classified into three levels: Unit Testing, Addition Testing, and System Testing. Whenever we think of developing any software we always concentrate on making the software bug free and most reliable. At this point of time Testing is used to make the software a bug free. Software Testing has been measured as the most important stage of the software development life cycle. Around 60% of resources and money are cast-off for the testing of software. Testing can be manual or automated. Software testing is an activity that emphases at assessing the competence of a program and commands that it truly meets the excellence results. There are many test cases that help in detecting the bugs so, in this paper we describe about the most commonly used test cases and testing techniques for the error detection.

On Empirically Examining The Effectiveness Of Deep Learning-Based Bug Localization Models

Software Bug Localization involves a significant amount of time and effort on the part of the software developer. Many state-of-the-art bug localization models have been proposed in the past, to help developers localize bugs easily. However, none of these models meet the adoption thresholds of the software practitioner. Recently some deep learning-based models have been proposed, that have been shown to perform better than the state-of-the-art models. With this motivation, we experiment on Convolution Neural Networks (CNNs) to examine their effectiveness in localizing bugs. We also train a SimpleLogistic model as a baseline model for our experiments. We train both our models on five open source Java projects and compare their performance across the projects. Our experiments show that the CNN models perform better than the SimpleLogistic models in most of the cases, but do not meet the adoption criteria set by the practitioners.