Presentation 2015-01-26
An Empirical Study on Requirements Elicitation from Feedback Comments Using LDA
Hitoshi TAKAHASHI, Hiroyuki NAKAGAWA, Tatsuhiro TSUCHIYA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Feedback comments, such as mailing list and reviews, include useful information for software developers. In this study, we try to automatically elicit software requirements from feedback comments. We use Latent Dirichlet Allocation (LDA), which is a promising way of topic modeling, for this elicitation. We applied it to two different sources, i.e., Apache Commons User List and App Store reviews, and discuss the feasibility and effectiveness of this approach for applying to these two different sources.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) requirements elicitation / feedback comments / LDA
Paper # KBSE2014-39
Date of Issue

Conference Information
Committee KBSE
Conference Date 2015/1/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Knowledge-Based Software Engineering (KBSE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Empirical Study on Requirements Elicitation from Feedback Comments Using LDA
Sub Title (in English)
Keyword(1) requirements elicitation
Keyword(2) feedback comments
Keyword(3) LDA
1st Author's Name Hitoshi TAKAHASHI
1st Author's Affiliation Department of Information and Computer Sciences, School of Engineering Science, Osaka University()
2nd Author's Name Hiroyuki NAKAGAWA
2nd Author's Affiliation Graduate School of Infomation Science and Technology, Osaka University
3rd Author's Name Tatsuhiro TSUCHIYA
3rd Author's Affiliation Graduate School of Infomation Science and Technology, Osaka University
Date 2015-01-26
Paper # KBSE2014-39
Volume (vol) vol.114
Number (no) 420
Page pp.pp.-
#Pages 6
Date of Issue