TY - JOUR
T1 - Not all bug reopens are negative
T2 - A case study on eclipse bug reports
AU - Mi, Qing
AU - Keung, Jacky
AU - Huo, Yuqi
AU - Mensah, Solomon
N1 - Publisher Copyright:
© 2018 Elsevier B.V.
PY - 2018/7
Y1 - 2018/7
N2 - Context: We observed a special type of bug reopen that has no direct impact on the user experience or the normal operation of the system being developed. We refer to these as non-negative bug reopens. Objective: Non-negative bug reopens are novel and somewhat contradictory to popular conceptions. Therefore, we thoroughly explored these phenomena in this study. Method: We begin with a novel approach that preliminarily characterizes non-negative bug reopens. Based on bug reports extracted from Eclipse Bugzilla, we then examined a case study to compare non-negative and regular bug reopens using the Wilcoxon-Mann-Whitney test. Results: The results show that non-negative bug reopens are statistically significantly different than regular bug reopens, based on their survival times and the number of developers involved in the entire debugging process. Conclusion: Taking into account the significant differences, we suggest that the effects of non-negative bug reopens should be considered in future research in related areas, such as bug triage and reopened bug prediction.
AB - Context: We observed a special type of bug reopen that has no direct impact on the user experience or the normal operation of the system being developed. We refer to these as non-negative bug reopens. Objective: Non-negative bug reopens are novel and somewhat contradictory to popular conceptions. Therefore, we thoroughly explored these phenomena in this study. Method: We begin with a novel approach that preliminarily characterizes non-negative bug reopens. Based on bug reports extracted from Eclipse Bugzilla, we then examined a case study to compare non-negative and regular bug reopens using the Wilcoxon-Mann-Whitney test. Results: The results show that non-negative bug reopens are statistically significantly different than regular bug reopens, based on their survival times and the number of developers involved in the entire debugging process. Conclusion: Taking into account the significant differences, we suggest that the effects of non-negative bug reopens should be considered in future research in related areas, such as bug triage and reopened bug prediction.
KW - Bug report
KW - Data quality
KW - Empirical software engineering
KW - Non-negative bug reopen
KW - Open source software
KW - Reopen cycle
UR - http://www.scopus.com/inward/record.url?scp=85043250300&partnerID=8YFLogxK
U2 - 10.1016/j.infsof.2018.03.006
DO - 10.1016/j.infsof.2018.03.006
M3 - Article
AN - SCOPUS:85043250300
SN - 0950-5849
VL - 99
SP - 93
EP - 97
JO - Information and Software Technology
JF - Information and Software Technology
ER -