Presentation 2002/3/7
Text Classification using Features of Educational Contents
Akira KITAUCHI, Toru TAKAKI, Ken'ichiro YAMAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose three methods for the classification of educational contents based on features of reference books for students. The document in the reference books has the following features: 1) the vocabulary is smaller than in news articles, 2) an important word in one document is used in the following documents repeatedly because students learn more difficult things step by step, and 3) a specific expression appears in the document. Using these features, we classify documents with three methods: gradual document classification, priority to previous documents, and extraction of important words in each document. Experimental evaluation using the educational reference books shows that each proposed method improves the classification accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Text categorization / Educational contents
Paper # NLC2001-91
Date of Issue

Conference Information
Committee NLC
Conference Date 2002/3/7(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) Text Classification using Features of Educational Contents
Sub Title (in English)
Keyword(1) Text categorization
Keyword(2) Educational contents
1st Author's Name Akira KITAUCHI
1st Author's Affiliation NTT Data Corporation()
2nd Author's Name Toru TAKAKI
2nd Author's Affiliation NTT Data Corporation
3rd Author's Name Ken'ichiro YAMAMOTO
3rd Author's Affiliation Telecommunications Advancement Organization of Japan
Date 2002/3/7
Paper # NLC2001-91
Volume (vol) vol.101
Number (no) 711
Page pp.pp.-
#Pages 8
Date of Issue