Transformer-based bug/feature classification

buir.contributor.authorÖztürk, Ceyhun Emre
buir.contributor.orcidÖztürk, Ceyhun Emre|0000-0001-9744-6778
dc.citation.epage4en_US
dc.citation.spage1
dc.contributor.authorÖztürk, Ceyhun Emre
dc.contributor.authorYılmaz, E. H.
dc.contributor.authorKöksal, Ö.
dc.coverage.spatialİstanbul, Türkiye
dc.date.accessioned2024-03-22T06:35:30Z
dc.date.available2024-03-22T06:35:30Z
dc.date.issued2023-08-28
dc.departmentDepartment of Electrical and Electronics Engineering
dc.descriptionDate of Conference: 05-08 July 2023
dc.descriptionConference Name: 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023
dc.description.abstractAutomatic classification of a software bug report as a 'bug' or 'feature' is essential to accelerate closed-source software development. In this work, we focus on automating the bug/feature classification task with artificial intelligence using a newly constructed dataset of Turkish software bug reports collected from a commercial project. We train and test support vector machine (SVM), k-nearest neighbors (KNN), convolutional neural network (CNN), transformer-based models, and similar artificial intelligence models on the collected reports. Results of the experiments show that transformer-based BERTurk is the best-performing model for the bug/feature classification task.
dc.description.abstractYazılım hata raporları için otomatik hata-istek tahmini yapılması, kapalı kaynak yazılım geliştirme sürecini hızlandırmak için önemlidir. Bu çalışmada, bir ticari yazılım geliştirme projesinden toplanan Türkçe hata raporları kullanılarak yeni bir veri kümesi oluşturulmuş ve hata-istek sınıflandırmasının yapay zeka ile otomatikleştirilmesine odaklanılmıştır. Bu kapsamda, destek vektör makinesi (SVM), k en yakın komşu (KNN), evrişimsel sinir ağı (CNN), dönüştürücü tabanlı modeller ve benzeri yapay zeka algoritmaları ve modelleri kullanılmıştır. Deney sonuçlarına göre hata-istek sınıflandırmada en iyi performans dönüştürücü tabanlı BERTurk modeli ile elde edilmiştir.
dc.description.provenanceMade available in DSpace on 2024-03-22T06:35:30Z (GMT). No. of bitstreams: 1 Transformer-based_bug_feature_classification.pdf: 443694 bytes, checksum: 54fc72ddb5f4359e958980904bedaffe (MD5) Previous issue date: 2023-08en
dc.identifier.doi10.1109/SIU59756.2023.10223806
dc.identifier.eisbn9798350343557
dc.identifier.isbn9798350343564
dc.identifier.issn2165-0608
dc.identifier.urihttps://hdl.handle.net/11693/115074
dc.language.isoTurkish
dc.publisherIEEE - Institute of Electrical and Electronics Engineers
dc.relation.isversionofhttps://dx.doi.org/10.1109/SIU59756.2023.10223806
dc.source.title2023 31st Signal Processing and Communications Applications Conference (SIU 2023)
dc.subjectSoftware bug report classification
dc.subjectNatural language processing
dc.subjectPre-trained language models
dc.subjectBERT
dc.subjectYazılım hata raporu sınıflandırma
dc.subjectDoğal dil işleme
dc.subjectÖn eğitimli dil modelleri
dc.titleTransformer-based bug/feature classification
dc.title.alternativeDönüştürücü tabanlı hata-istek sınıflandırma
dc.typeConference Paper

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Transformer-based_bug_feature_classification.pdf
Size:
433.29 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.01 KB
Format:
Item-specific license agreed upon to submission
Description: