Automated defect prioritization based on defects resolved at various project periods

Name: Automated defect prioritization based on defects resolved at various project periods
Author: Gökçeoğlu, M., Sözer, Hasan

İsim	Automated defect prioritization based on defects resolved at various project periods
Yazar	Gökçeoğlu, M., Sözer, Hasan
Basım Tarihi:	2021-09
Basım Yeri	- Elsevier
Konu	Defect prioritization, Industrial case study, Machine learning, Process automation, Software maintenance
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	0164-1212
Kayıt Numarası	7a70e428-13a8-4e59-922e-5b75b2ee0d71
Lokasyon	Computer Science
Tarih	2021-09
Örnek Metin	Defect prioritization is mainly a manual and error-prone task in the current state-of-the-practice. We evaluated the effectiveness of an automated approach that employs supervised machine learning. We used two alternative techniques, namely a Naive Bayes classifier and a Long Short-Term Memory model. We performed an industrial case study with a real project from the consumer electronics domain. We compiled more than 15,000 issues collected over 3 years. We could reach an accuracy level up to 79.36% and we had 3 observations. First, Long Short-Term Memory model has a better accuracy when compared with a Naive Bayes classifier. Second, structured features lead to better accuracy compared to textual descriptions. Third, accuracy is not improved by considering increasingly earlier defects as part of the training data. Increasing the size of the training data even decreases the accuracy compared to the results, when we use data only regarding the recently resolved defects.
DOI	10.1016/j.jss.2021.110993
Cilt	179

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Automated defect prioritization based on defects resolved at various project periods

Yazar Gökçeoğlu, M., Sözer, Hasan

Basım Tarihi 2021-09

Basım Yeri - Elsevier

Konu Defect prioritization, Industrial case study, Machine learning, Process automation, Software maintenance

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 0164-1212

Kayıt Numarası 7a70e428-13a8-4e59-922e-5b75b2ee0d71

Lokasyon Computer Science

Tarih 2021-09

Örnek Metin Defect prioritization is mainly a manual and error-prone task in the current state-of-the-practice. We evaluated the effectiveness of an automated approach that employs supervised machine learning. We used two alternative techniques, namely a Naive Bayes classifier and a Long Short-Term Memory model. We performed an industrial case study with a real project from the consumer electronics domain. We compiled more than 15,000 issues collected over 3 years. We could reach an accuracy level up to 79.36% and we had 3 observations. First, Long Short-Term Memory model has a better accuracy when compared with a Naive Bayes classifier. Second, structured features lead to better accuracy compared to textual descriptions. Third, accuracy is not improved by considering increasingly earlier defects as part of the training data. Increasing the size of the training data even decreases the accuracy compared to the results, when we use data only regarding the recently resolved defects.

DOI 10.1016/j.jss.2021.110993

Cilt 179