Presentation 2008-02-07
Reputation Information Retrieval Support System Using Relationship Between Review and Score of Each Attribute
Takayuki YAMADA, Yoshiaki YASUMURA, Kuniaki UEHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a reputation information retrieval support system which displays detailed reputation information. From the keywords that user inputs, this system displays reputation information and its polarity (positive or negative) of each attribute. First, polar sentence dictionary of each attribute are created by learning relationship between a review and its score. Next, reputation information is classified into attribute categories and the polarity of reputation information is decided (P/N classification) by using the dictionary. Finally, Web browser displays reputation information of each attribute. Experimental results show that the accuracy of attribute classification is 79.9%, the P/N classification in P documents is 89.4%, and the P/N classification in N documents is 65.6%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Text Mining / Text Classification / Reputation Information Retrieval / Attribute
Paper # NLC2007-87
Date of Issue

Conference Information
Committee NLC
Conference Date 2008/1/31(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Reputation Information Retrieval Support System Using Relationship Between Review and Score of Each Attribute
Sub Title (in English)
Keyword(1) Text Mining
Keyword(2) Text Classification
Keyword(3) Reputation Information Retrieval
Keyword(4) Attribute
1st Author's Name Takayuki YAMADA
1st Author's Affiliation Graduate School of Science and Technology, Kobe University()
2nd Author's Name Yoshiaki YASUMURA
2nd Author's Affiliation Graduate School of Engineering, Kobe University
3rd Author's Name Kuniaki UEHARA
3rd Author's Affiliation Graduate School of Engineering, Kobe University
Date 2008-02-07
Paper # NLC2007-87
Volume (vol) vol.107
Number (no) 480
Page pp.pp.-
#Pages 6
Date of Issue