DENATURE: duplicate detection and type identification in open source bug repositories

Chauhan, R. P.; Sharma, Shakshi; Goyal, Anjali

doi:10.1007/s13198-023-01855-x

Cited by 2 publications

(2 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IR excels in accurate feature extraction, while ML outperforms in similarity analysis, recommendation, and prediction. Some works have already proposed methods based on this idea [30,31]. Secondly, optimizing the application of the latest advances in machine learning and information retrieval, such as transformer models used in large-scale language processing, after appropriate transfer learning may lead to better results than the current models.…”

Section: Overview Of Relevant Literature In Recent Yearsmentioning

confidence: 99%

“…The second model is aimed at modeling bugs and predicting the most suitable developer to fix a particular bug. Chauhan et al proposed DENATURE, a method that combines information retrieval (IR) and machine learning (ML) techniques for detection of duplicate bug reports and bug triage [30]. They first convert bug reports into TF-IDF vectors using an IR-based approach and calculate cosine similarity to determine if bug reports are duplicates.…”

Section: Machine Learning Approaches For Deduplication and Triagementioning

confidence: 99%

See 1 more Smart Citation

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

Qian,

Zhang,

Nie

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

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.

show abstract

Section: Overview Of Relevant Literature In Recent Yearsmentioning

confidence: 99%

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

Applied Sciences

View full text Add to dashboard Cite

show abstract

Automatic Bug Triaging Process: An Enhanced Machine Learning Approach through Large Language Models

Chhabra,

Chadha

2024

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Bug resolution and maintenance are the most critical phases of the software development life cycle. The traditional bug triaging concept refers to the manual assignment of bugs to the appropriate developer after reading the bug details from the bug tracker and further resolving it. The advent of machine learning algorithms provides various solutions for automated bug triaging. Machine learning algorithms can be used to classify bugs and assign each to a developer. Reducing manual efforts optimizes bug-triaging by utilizing manpower in other software development processes. Furthermore, machine learning Large Language Models (LLMs) can be used to take advantage of their natural language processing features and capabilities. This study proposes a machine learning-based embed chain LLM approach for automatic bug triaging. This approach is used to automatically classify bug reports. Based on the results, the appropriate developer is recommended. In addition, the proposed approach is used to automatically predict the priority of bug reports. This paper also discusses the strengths and challenges of the proposed approach.

show abstract

DENATURE: duplicate detection and type identification in open source bug repositories

Cited by 2 publications

References 56 publications

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

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

Automatic Bug Triaging Process: An Enhanced Machine Learning Approach through Large Language Models

Contact Info

Product

Resources

About