Presentation 2018-12-07
Feature Selection for Document Classification focused on Support Vector
Kota Sakasegawa, Sachio Hirokawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Feature selection is a well-known approach for improving the prediction performance of document classifcation, where crucial words are selected and used in vectorization of the documents. This paper proposes an improvement of feature selection of [Sakai & Hirokawa 2012] by considering the occurences of words in ths support vectors. We conducted the evaluation of the proposed method on reuter dataset and confirmed that the proposed method yields allmost the same performance with a small number of feature words.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) document classifcation / machine learning / feature selection / SVM
Paper # AI2018-25
Date of Issue 2018-11-30 (AI)

Conference Information
Committee AI
Conference Date 2018/12/7(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tsunenori Mine(Kyushu Univ.)
Vice Chair Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.)
Secretary Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.)
Assistant Yuko Sakurai(AIST)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Feature Selection for Document Classification focused on Support Vector
Sub Title (in English)
Keyword(1) document classifcation
Keyword(2) machine learning
Keyword(3) feature selection
Keyword(4) SVM
1st Author's Name Kota Sakasegawa
1st Author's Affiliation Kyushu University(Kyushu Univ.)
2nd Author's Name Sachio Hirokawa
2nd Author's Affiliation Kyushu University(Kyushu Univ.)
Date 2018-12-07
Paper # AI2018-25
Volume (vol) vol.118
Number (no) AI-350
Page pp.pp.1-4(AI),
#Pages 4
Date of Issue 2018-11-30 (AI)