Presentation 2023-03-15
Investigation of software development history using a configuration management tool for defect prediction
Takayuki Zukawa, Masanari Kondo, Eunjong Choi, Osamu Mizuno,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) As software becomes more widely used, Infrastructure as Code (IaC) is becoming increasingly popular for eliminating the need for human intervention and improving the efficiency in system operation. However, defects in IaC can lead to serious problems such as loss of customer data and economic loss. In this study, we focus on defect-fixing commits in Ansible and investigate whether vectorizing natural language information in commit messages can predict defect-fixing commits. By using BOW, we achieved an accuracy of 0.869 for AUC and 0.782 for F1-score in classifying commit messages. Additionally, we obtained an accuracy of 0.665 for AUC and 0.313 for F1-score in classifying commit message categories.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Defect prediction / Mining Software Repositories / Infrastructure as Code / Ansible
Paper # SS2022-64
Date of Issue 2023-03-07 (SS)

Conference Information
Committee SS
Conference Date 2023/3/14(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kozo Okano(Shinshu Univ.)
Vice Chair Yoshiki Higo(Osaka Univ.)
Secretary Yoshiki Higo(Shinshu Univ.)
Assistant Shinsuke Matsumoto(Osaka Univ.)

Paper Information
Registration To Technical Committee on Software Science
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Investigation of software development history using a configuration management tool for defect prediction
Sub Title (in English)
Keyword(1) Defect prediction
Keyword(2) Mining Software Repositories
Keyword(3) Infrastructure as Code
Keyword(4) Ansible
1st Author's Name Takayuki Zukawa
1st Author's Affiliation Kyoto Institute of technology(Kyoto Inst. Tech.)
2nd Author's Name Masanari Kondo
2nd Author's Affiliation Kyushu University(Kyushu Univ.)
3rd Author's Name Eunjong Choi
3rd Author's Affiliation Kyoto Institute of technology(Kyoto Inst. Tech.)
4th Author's Name Osamu Mizuno
4th Author's Affiliation Kyoto Institute of technology(Kyoto Inst. Tech.)
Date 2023-03-15
Paper # SS2022-64
Volume (vol) vol.122
Number (no) SS-432
Page pp.pp.103-108(SS),
#Pages 6
Date of Issue 2023-03-07 (SS)