Software Module Classification for Commercial Bug Reports

Öztürk, Ceyhun E.; Yılmaz, Eyüp Halit; Köksal, Ömer; Koç, Aykut

doi:10.1109/icasspw59220.2023.10193706

Cited by 2 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They use SVM and CNN models to process these texts and predict the suitable development teams for the bug reports. Öztürk et al [17] utilize several ML methods to predict the related software modules for the bug reports of a closed-source software project. Since there is a dedicated development team for each module, Öztürk et al [17] actually find suitable development teams for the bug reports.…”

Section: Related Workmentioning

confidence: 99%

“…Öztürk et al [17] utilize several ML methods to predict the related software modules for the bug reports of a closed-source software project. Since there is a dedicated development team for each module, Öztürk et al [17] actually find suitable development teams for the bug reports. They utilize sequential deep learning algorithms and transformer-based language models.…”

Section: Related Workmentioning

confidence: 99%

“…Turkish software bug report classification literature is an emerging one with a number of pioneering studies [17,9]. Köksal and Tekinerdogan [9] classify bug types of Turkish bug reports using traditional ML algorithms, such as support vector machine (SVM) and k-nearest neighbors (KNN).…”

Section: Introductionmentioning

confidence: 99%

“…Köksal and Tekinerdogan [9] classify bug types of Turkish bug reports using traditional ML algorithms, such as support vector machine (SVM) and k-nearest neighbors (KNN). On the other hand, Öztürk et al [17] utilize sequential deep learning algorithms, such as gated recurrent unit (GRU) and CNN; and transformer-based language models, such as BERTurk [15,18], as well. We provide an extension of the work of Öztürk et al [17] employing various ML methods to the module classification task, which aims to assign software bug reports to the correct software modules.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, Öztürk et al [17] utilize sequential deep learning algorithms, such as gated recurrent unit (GRU) and CNN; and transformer-based language models, such as BERTurk [15,18], as well. We provide an extension of the work of Öztürk et al [17] employing various ML methods to the module classification task, which aims to assign software bug reports to the correct software modules. We extend this work by utilizing ensemble learning on the TSBR datasets that target the module, developer, and issue/feature classification tasks.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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%

Section: Related Workmentioning

confidence: 99%