Author
Gökçeoğlu, M., Sözer, Hasan
Publication Date
2021-09
Publication Place
-
Elsevier
Subject
Defect prioritization, Industrial case study, Machine learning, Process automation, Software maintenance
Type
Periodical
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
0164-1212
Record ID
7a70e428-13a8-4e59-922e-5b75b2ee0d71
Library Location
Computer Science
Date
2021-09
Sample Text
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
