A Machine Learning Approach to Identification of the Corresponding NDC Numbers for NDLSH with Sub-headings
-
- TANIGUCHI Shoichi
- School of Library and Information Science, Keio University
-
- KIMURA Maiko
- JSPS Research Fellow, Institute for Advanced Studies on Asia, The University of Tokyo, currently at School of Library and Information Science, Keio University
Bibliographic Information
- Other Title
-
- 機械学習によってNDLSH細目付き件名標目に対するNDC代表分類記号を同定する試み
- キカイ ガクシュウ ニ ヨッテ NDLSH サイモク ツキ ケンメイ ヒョウモク ニ タイスル NDC ダイヒョウ ブンルイ キゴウ オ ドウテイ スル ココロミ
Search this article
Abstract
National Diet Library Subject Headings (NDLSH) with sub-headings do not have in principle their corresponding classification numbers, unlike those without sub-headings. This study tries to identify the proper combination among the NDLSH with NDC number pairs extracted from bibliographic re-cords by utilizing machine learning methods.<br> First, adequacy of an individual pairing of a subject heading with a NDC number in a bibliographic record was judged manually for over 10,000 pairs. They were then used as training and evaluation data in machine learning experiments. About 80 percent of the pairs were eventually judged as proper com-binations, which had either a) the same classification numbers as, or b) the classification numbers being forward-matched with, the corresponding numbers for the main headings included in subject headings.<br> Then, machine learning experiments were conducted with the manually judged pairs of subject headings and NDC numbers, whose results were evaluated in a cross validation manner. Two ways of establishing training data sets, five inclusive attribute sets of individual pairs, and seven major machine learning methods, were adopted in the experiments. The results showed that the machine learning approach to the issue had a certain effectiveness, but was not highly effective.
Journal
-
- Journal of Japan Society of Library and Information Science
-
Journal of Japan Society of Library and Information Science 64 (2), 59-76, 2018
Japan Society of Library and Information Science
- Tweet
Details 詳細情報について
-
- CRID
- 1390564237996860800
-
- NII Article ID
- 130007393769
- 40021570119
-
- NII Book ID
- AA11333306
-
- ISSN
- 24324027
- 13448668
-
- NDL BIB ID
- 029053243
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed