Presentation 2019-01-26
Automatic book classification using neural networks
Haruki Sugiyama, Yoshinori Tanabe,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) There are many studies applying machine learning to classify books by the Nippon Decimal Classification (NDC), a system widely applied in Japan. However, few among them employ neural networks. In this paper, we report the experimental results of automatic classification of books using basic multilayer perceptron models, convolutional neural networks (CNN), and recurrent neural networks (RNN). We collected data of 40,005 books from internet shopping mall Rakuten Ichiba. They are book titles, merchandise information, author, and publisher. Feature words were selected using Jaccard coefficients and other factors after morphological analysis, and they were converted to word vectors using Asahi Shimbun Word Vector. Precisions obtained from experiments are: 77% by multi-layer perceptron models, 71% by CNN, and 74% by RNN.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) NDC / Machine Learning / Automatic classification / Neural Networks
Paper # KBSE2018-53
Date of Issue 2019-01-19 (KBSE)

Conference Information
Committee KBSE
Conference Date 2019/1/26(1days)
Place (in Japanese) (See Japanese page)
Place (in English) NII
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Fumihiro Kumeno(Nippon Inst. of Tech.)
Vice Chair Hiroyuki Nakagawa(Osaka Univ.)
Secretary Hiroyuki Nakagawa(NTT)
Assistant Ryuichi Takahashi(Ibaraki Univ.) / Yoshinori Tanabe(Tsurumi Univ.)

Paper Information
Registration To Technical Committee on Knowledge-Based Software Engineering
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic book classification using neural networks
Sub Title (in English)
Keyword(1) NDC
Keyword(2) Machine Learning
Keyword(3) Automatic classification
Keyword(4) Neural Networks
1st Author's Name Haruki Sugiyama
1st Author's Affiliation Tsurumi University(Tsurumi Univ.)
2nd Author's Name Yoshinori Tanabe
2nd Author's Affiliation Tsurumi University(Tsurumi Univ.)
Date 2019-01-26
Paper # KBSE2018-53
Volume (vol) vol.118
Number (no) KBSE-425
Page pp.pp.61-66(KBSE),
#Pages 6
Date of Issue 2019-01-19 (KBSE)