A spatial–temporal graph neural network framework for automated software bug triaging

The Issue Tracking System (ITS) repositories are rich sources of software development documentation that are useful in assessing the status and quality of software projects. An original model is proposed for tracing issue handling activities and their impact on project progress. As opposed to classical data mining of software repositories, we consider fine-grained features of issues which provide a better insight into project evolution. A thorough analysis of repository contents allows us to define useful metrics for characterizing issue handling schemes. These metrics are derived from the introduced graph model and developed original data mining algorithms targeting timing, issue flow progress and project actor activity aspects. This study is associated with issue processing states and their sequences (handling paths), leading to problem resolution. The introduced taxonomy of issue processing schemes facilitates the creation of a pertinent knowledge database and the identification of both bad (anomalies) and good practices. The proposed approach is illustrated with experimental results related to a representative set of ITS project repositories. These results enhance experts’ knowledge of the project and can be used for correct decision-making actions. They reveal weak points in project development and possible directions for improvement.

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Section: Issue Preprocessing Algorithm (A1)mentioning

confidence: 99%

Graph-Driven Exploration of Issue Handling Schemes in Software Projects

Dobrzyński,

Sosnowski

2024

“…The first type is the bug report, which includes the bug's category, the platform it occurred on, the components involved, priority, the personnel involved, and some real-time records. Typical bug reports, as shown in Figure 2, are generally semistructured files that contain various information [9,10]. The content includes the context of the crashing thread, such as the stack trace and processor registers, as well as a subset of the machine memory contents at the time of the crash.…”

Section: Reportermentioning

confidence: 99%

“…Wu et al built upon the developer collaboration network (DCN) and considered the interaction between developers to propose the ST-DGNN model for bug triaging [9]. It includes the joint random walk (JRWalk) mechanism and a graph recurrent convolutional neuron network (GRCNN).…”

Section: Machine Learning Approaches For Deduplication and Triagementioning

confidence: 99%

A Survey on Bug Deduplication and Triage Methods from Multiple Points of View

Qian,

Zhang,

Nie

et al. 2023

To address the issue of insufficient testing caused by the continuous reduction of software development cycles, many organizations maintain bug repositories and bug tracking systems to ensure real-time updates of bugs. However, each day, a large number of bugs is discovered and sent to the repository, which imposes a heavy workload on bug fixers. Therefore, effective bug deduplication and triage are of great significance in software development. This paper provides a comprehensive investigation and survey of the recent developments in bug deduplication and triage. The study begins by outlining the roadmap of the existing literature, including the research trends, mathematical models, methods, and commonly used datasets in recent years. Subsequently, the paper summarizes the general process of the methods from two perspectives—runtime information-based and bug report-based perspectives—and provides a detailed overview of the methodologies employed in relevant works. Finally, this paper presents a detailed comparison of the experimental results of various works in terms of usage methods, datasets, accuracy, recall rate, and F1 score. Drawing on key findings, such as the need to improve the accuracy of runtime information collection and refine the description information in bug reports, we propose several potential future research directions in the field, such as stack trace enrichment and the combination of new NLP models.

“…To inform the learning, we constructed a bug tossing knowledge graph which incorporates not only goal-oriented component tossing relationships but also rich information about component tossing community, component descriptions, and historical closed and tossed bugs, from which three categories and seven types of features for bug, component, and bug-component relation can be derived. Wu et al [34] proposed a novel spatial-temporal dynamic graph neural network (ST-DGNN) framework, including a joint random walk (JRWalk) mechanism and a graph recurrent convolutional neural network (GRCNN) model. Guo et al [35] presented a new automatic bug triaging approach which is based on convolution neural network (CNN) and developer activities.…”

Section: Related Workmentioning

confidence: 99%

Automatic Bug Triaging via Deep Reinforcement Learning

Liu

Zhang

et al. 2022

Software maintenance and evolution account for approximately 90% of the software development process (e.g., implementation, testing, and maintenance). Bug triaging refers to an activity where developers diagnose, fix, test, and document bug reports during software development and maintenance to improve the speed of bug repair and project progress. However, the large number of bug reports submitted daily increases the triaging workload, and open-source software has a long maintenance cycle. Meanwhile, the developer activity is not stable and changes significantly during software development. Hence, we propose a novel bug triaging model known as auto bug triaging via deep reinforcement learning (BT-RL), which comprises two models: a deep multi-semantic feature (DMSF) fusion model and an online dynamic matching (ODM) model. In the DMSF model, we extract relevant information from bug reports to obtain high-quality feature representation. In the ODM model, through bug report analysis and developer activities, we use a strategy based on the reinforcement learning framework, through which we perform training while learning and recommend developers for bug reports. Extensive experiments on open-source datasets show that the BT-RL method outperforms state-of-the-art methods in bug triaging.