Presentation 2011-03-09
Analysis of Rakuten GORA reviews
Tomoko FUKUI, Hidenori KAWAMURA, Keiji SUZUKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In these days, the internet, chat and weblog have lowered our barriers to the posting comments and information on Web sites. Because they are easy to use, their users are increasing yearly. These comments and information involve user's opinions, impressions and evaluations of certain objects, so there is a need for extraction of valuable information from these comments posted by many people. But it is harder to analyze those free descriptions quantitatively than to analyze numerical data. In this paper, we propose an estimation approach by using Rakuten GORA reviews. It estimates 5-point scale from free descriptions. First, we extract nouns related to each question and words of modification relation. Second, we analyze relationship between distributions of 5-point scales and those extracted words and find an estimation approach. Then we apply that method to the other reviews and compare estimation result to real data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) text mining / free description / 5-point scale
Paper # AI2010-61
Date of Issue

Conference Information
Committee AI
Conference Date 2011/3/1(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 Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Analysis of Rakuten GORA reviews
Sub Title (in English)
Keyword(1) text mining
Keyword(2) free description
Keyword(3) 5-point scale
1st Author's Name Tomoko FUKUI
1st Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University()
2nd Author's Name Hidenori KAWAMURA
2nd Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
3rd Author's Name Keiji SUZUKI
3rd Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
Date 2011-03-09
Paper # AI2010-61
Volume (vol) vol.110
Number (no) 462
Page pp.pp.-
#Pages 4
Date of Issue