Presentation 2007-01-23
P/N Classification for Reputation Extraction from BBS
Keisuke TAKEUCHI, Akira URASIMA, Minoru HATADA, Shoryu ATAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper reports on the P/N classification system for the documents that include reputation information. The P/N classification system divides documents into positive and negative ones. We employ 3 words (adjective or adjective noun, noun prior them and posterior negative expression "nai") dictionary while past study employ one word (adjective or adjective noun) dictionary. The dictionary entries has own score calculated by Training data and P/N Classification is derived from them. The result of the experiment was that the success rate was 78.5% in past study and 87.5% in our study.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reputation extraction / Text mining / Document classification / Scoring
Paper # KBSE2006-64
Date of Issue

Conference Information
Committee KBSE
Conference Date 2007/1/16(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) P/N Classification for Reputation Extraction from BBS
Sub Title (in English)
Keyword(1) Reputation extraction
Keyword(2) Text mining
Keyword(3) Document classification
Keyword(4) Scoring
1st Author's Name Keisuke TAKEUCHI
1st Author's Affiliation Toyama Prefectural University()
2nd Author's Name Akira URASIMA
2nd Author's Affiliation Toyama Prefectural University
3rd Author's Name Minoru HATADA
3rd Author's Affiliation Toyama Prefectural University
4th Author's Name Shoryu ATAKA
4th Author's Affiliation Toyama Prefectural University
Date 2007-01-23
Paper # KBSE2006-64
Volume (vol) vol.106
Number (no) 473
Page pp.pp.-
#Pages 6
Date of Issue