Presentation 2002/7/12
The performance of subject estimation and discrimination methods for educational Web resources
Minoru NAKAYAMA, Yasutaka SHIMIZU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The purpose of this study is to compare performance among developed subject discrimination methods for educational Web resources. Three methods are vector space model (VSM) using degree of cosine similarity, vector distance on the self-organizing map (SOM) and three layer percptron (MLP). The 403 teaching schemes were prepared as the test documents for the subject discrimination. The recall rate using MLP is the highest for most subjects. The highest precision rate among the methods depend on subject. As a result, F1 measure as total performance index of most subjects are the highest for the method using MLP.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) educational information / web resources / document discrimination performance / SOM / MLP
Paper # ET2002-25
Date of Issue

Conference Information
Committee ET
Conference Date 2002/7/12(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 Educational Technology (ET)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The performance of subject estimation and discrimination methods for educational Web resources
Sub Title (in English)
Keyword(1) educational information
Keyword(2) web resources
Keyword(3) document discrimination performance
Keyword(4) SOM
Keyword(5) MLP
1st Author's Name Minoru NAKAYAMA
1st Author's Affiliation CRADLE, Tokyo Institute of Technology()
2nd Author's Name Yasutaka SHIMIZU
2nd Author's Affiliation Educational Resource Center, National Institute of Educational Policy Research
Date 2002/7/12
Paper # ET2002-25
Volume (vol) vol.102
Number (no) 222
Page pp.pp.-
#Pages 6
Date of Issue