期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：8
页码：285-294
出版社：Science and Information Society (SAI)
摘要：In Software Development Life Cycle, fixing defect
bugs is one of the essential activities of the software maintenance
phase. Bug severity indicates how major or minor the bug
impacts on the execution of the system and how rapidly the
developer should fix it. Triaging a vast amount of new bugs
submitted to the software bug repositories is a cumbersome and
time-consuming process. Manual triage might lead to a mistake
in assigning the appropriate severity level for each bug. As a
consequence, a delay for fixing severe software bugs will take
place. However, the whole process of assigning the severity level
for bug reports should be automated. In this paper, we aim to
build prediction models that will be utilized to determine the
class of the severity (severe or non-severe) of the reported bug.
To validate our approach, we have constructed a dataset from
historical bug reports stored in JIRA bug tracking system. These
bug reports are related to different closed-source projects
developed by INTIX Company located in Amman, Jordan. We
compare eight popular machine learning algorithms, namely
Naive Bayes, Naive Bayes Multinomial, Support Vector Machine,
Decision Tree (J48), Random Forest, Logistic Model Trees,
Decision Rules (JRip) and K-Nearest Neighbor in terms of
accuracy, F-measure and Area Under the Curve (AUC).
According to the experimental results, a Decision Tree algorithm
called Logistic Model Trees achieved better performance
compared to other machine learning algorithms in terms of
Accuracy, AUC and F-measure with values of 86.31, 0.90 and
0.91, respectively.
