Classification of open source software bug report based on transfer learning

Liao, Zhifang; Wang, Kun; Zeng, Qi; Liu, Shengzong; Zhang, Yan; He, Jing

doi:10.1111/exsy.13184

Cited by 3 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This framework has a filter that finds out mislabeled samples. Zhifang et al [14] use the information of the people submitting bug reports as the features of bug reports to classify them. Their framework puts bug reports into two categories, i.e., bug or non-bug.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Bug Report Classification with Ensemble Learning for Closed-Source Software

Yılmaz,

Öztürk,

Köksal

2023

Preprint

View full text Add to dashboard Cite

This paper introduces a set of datasets grouped under the name Turkish Software Bug Reports (TSBR), which comprises commercial software bug reports from a closed-source project. We investigate and report the statistical properties and classification difficulty of the TSBR datasets. We employ various methods from the text classification literature to apply several classification tasks related to software development on the TSBR datasets. The methods we employ include traditional machine learning (ML) methods such as k-nearest neighbors (KNN) and random forest (RF); sequential deep learning (DL) models such as gated recurrent unit (GRU) and convolutional neural network (CNN); transformer-based language models; and ensembles of the employed models. Our work is among the first efforts in automated bug report classification literature that uses ensembles of DL models.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Thus, automatic issue/feature classification is a significant problem in software development. Some of the prior works [12,13] in literature utilize traditional ML methods to solve this problem, whereas others [6,14] use more advanced ML algorithms, such as BERT [15] and convolutional neural networks (CNN) [16].…”

Section: Introductionmentioning

confidence: 99%

Bug Report Classification with Ensemble Learning for Closed-Source Software

Yılmaz,

Öztürk,

Köksal

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Fan et al [2] and Pandey et al [3] classified issue reports into bug or non-bug using machine learning techniques. Zhu et al [6], Kallis et al [7], Kim et al [8], Zhifang, Liao, et al [9], and Cho et al [10] used deep learning techniques for the same task.…”

Section: Issue Report Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Researchers have conducted studies on automatically classifying issue reports to systematically manage issue reports [1][2][3][4][5][6][7][8][9][10]. Some of them [1][2][3]6,7,9] focused on classifying issue reports into a few categories, such as bug or non-bug. For example, Kallis et al [7] employed FastText to classify issue reports into three categories: Bug, Enhancement, and Question.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Multimodal Deep Learning Model Using Text, Image, and Code Data for Improving Issue Classification Tasks

Kwak,

Jung,

Lee

2023

Applied Sciences

View full text Add to dashboard Cite

Issue reports are valuable resources for the continuous maintenance and improvement of software. Managing issue reports requires a significant effort from developers. To address this problem, many researchers have proposed automated techniques for classifying issue reports. However, those techniques fall short of yielding reasonable classification accuracy. We notice that those techniques rely on text-based unimodal models. In this paper, we propose a novel multimodal model-based classification technique to use heterogeneous information in issue reports for issue classification. The proposed technique combines information from text, images, and code of issue reports. To evaluate the proposed technique, we conduct experiments with four different projects. The experiments compare the performance of the proposed technique with text-based unimodal models. Our experimental results show that the proposed technique achieves a 5.07% to 14.12% higher F1-score than the text-based unimodal models. Our findings demonstrate that utilizing heterogeneous data of issue reports helps improve the performance of issue classification.

show abstract