Presentation 2023-01-20
A study for using deep learning inference results of program defects in code review checklists
Kazuhiko Ogawa, Takako Nakatani,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In system development, various efforts are made to improve the quality of programs. One of these efforts is code review. We applied a system using deep learning, which we call the CNN-BI system, to infer program defects, and found that the accuracy (F value) of defects in SQL statements was 0.71. In this study, we created a checklist that includes the inference results of the CNN-BI system as checklist items. We examined the impact of the checklists with inference results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) code review / checklist / convolutional nural network / deep learning / bug inference
Paper # KBSE2022-51
Date of Issue 2023-01-12 (KBSE)

Conference Information
Committee KBSE
Conference Date 2023/1/19(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Takuya Saruwatari(NTT Data)
Vice Chair Yoshinori Tanabe(Tsurumi Univ.)
Secretary Yoshinori Tanabe(Osaka Inst. of Tech.)
Assistant Yoshitaka Aoki(BIPROGY) / Hiroki Horita(Ibaraki Univ.)

Paper Information
Registration To Technical Committee on Knowledge-Based Software Engineering
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study for using deep learning inference results of program defects in code review checklists
Sub Title (in English)
Keyword(1) code review
Keyword(2) checklist
Keyword(3) convolutional nural network
Keyword(4) deep learning
Keyword(5) bug inference
1st Author's Name Kazuhiko Ogawa
1st Author's Affiliation The Open University Of Japan(OUJ)
2nd Author's Name Takako Nakatani
2nd Author's Affiliation The Open University Of Japan(OUJ)
Date 2023-01-20
Paper # KBSE2022-51
Volume (vol) vol.122
Number (no) KBSE-345
Page pp.pp.46-51(KBSE),
#Pages 6
Date of Issue 2023-01-12 (KBSE)