Presentation 2020-10-19
A Prototype Tool to Predict Comment Line Positions for Code Review
Toshihiro Kamiya,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Comments in source code play an important role in code comprehension. This paper presents a method and its prototype tool that predicts the locations of comments in source code. This tool has an RNN which inputs a sequence of tokens (holding each comment as a special token) extracted from a given source file with lexical analysis, and outputs predict whether a token appearing a location should be a comment or not. For a given source file, the RNN is used to predict a comment that appears at each end of sentences. One of the tool's supposed applications is to support a code review by pointing out where comments are expected to be written but not written.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Souce code comprehension / Code review / Maintenance / Static analysis
Paper # SS2020-12,DC2020-29
Date of Issue 2020-10-12 (SS, DC)

Conference Information
Committee DC / SS
Conference Date 2020/10/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hiroshi Takahashi(Ehime Univ.) / Takashi Kobayashi(Tokyo Inst. of Tech.)
Vice Chair Tatsuhiro Tsuchiya(Osaka Univ.) / Kozo Okano(Shinshu Univ.)
Secretary Tatsuhiro Tsuchiya(Nihon Univ.) / Kozo Okano(Chiba Univ.)
Assistant / Shinpei Ogata(Shinshu Univ.)

Paper Information
Registration To Technical Committee on Dependable Computing / Technical Committee on Software Science
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Prototype Tool to Predict Comment Line Positions for Code Review
Sub Title (in English)
Keyword(1) Souce code comprehension
Keyword(2) Code review
Keyword(3) Maintenance
Keyword(4) Static analysis
1st Author's Name Toshihiro Kamiya
1st Author's Affiliation Shimane University(Shimane Univ.)
Date 2020-10-19
Paper # SS2020-12,DC2020-29
Volume (vol) vol.120
Number (no) SS-193,DC-194
Page pp.pp.43-48(SS), pp.43-48(DC),
#Pages 6
Date of Issue 2020-10-12 (SS, DC)