Transformer-based bug/feature classification
buir.contributor.author | Öztürk, Ceyhun Emre | |
buir.contributor.orcid | Öztürk, Ceyhun Emre|0000-0001-9744-6778 | |
dc.citation.epage | 4 | en_US |
dc.citation.spage | 1 | |
dc.contributor.author | Öztürk, Ceyhun Emre | |
dc.contributor.author | Yılmaz, E. H. | |
dc.contributor.author | Köksal, Ö. | |
dc.coverage.spatial | İstanbul, Türkiye | |
dc.date.accessioned | 2024-03-22T06:35:30Z | |
dc.date.available | 2024-03-22T06:35:30Z | |
dc.date.issued | 2023-08-28 | |
dc.department | Department of Electrical and Electronics Engineering | |
dc.description | Date of Conference: 05-08 July 2023 | |
dc.description | Conference Name: 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023 | |
dc.description.abstract | Automatic 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.abstract | Yazılım 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.provenance | Made 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: 2023-08 | en |
dc.identifier.doi | 10.1109/SIU59756.2023.10223806 | |
dc.identifier.eisbn | 9798350343557 | |
dc.identifier.isbn | 9798350343564 | |
dc.identifier.issn | 2165-0608 | |
dc.identifier.uri | https://hdl.handle.net/11693/115074 | |
dc.language.iso | Turkish | |
dc.publisher | IEEE - Institute of Electrical and Electronics Engineers | |
dc.relation.isversionof | https://dx.doi.org/10.1109/SIU59756.2023.10223806 | |
dc.source.title | 2023 31st Signal Processing and Communications Applications Conference (SIU 2023) | |
dc.subject | Software bug report classification | |
dc.subject | Natural language processing | |
dc.subject | Pre-trained language models | |
dc.subject | BERT | |
dc.subject | Yazılım hata raporu sınıflandırma | |
dc.subject | Doğal dil işleme | |
dc.subject | Ön eğitimli dil modelleri | |
dc.title | Transformer-based bug/feature classification | |
dc.title.alternative | Dönüştürücü tabanlı hata-istek sınıflandırma | |
dc.type | Conference Paper |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Transformer-based_bug_feature_classification.pdf
- Size:
- 433.29 KB
- Format:
- Adobe Portable Document Format
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 2.01 KB
- Format:
- Item-specific license agreed upon to submission
- Description: