Suggesting Japanese subject headings using web information resources

• Published in: Proceedings of the ASIST Annual Meeting Vol. 43; no. 1; pp. 1 - 6
• Main Authors: Ueda, Hiroshi, Murakami, Harumi
• Format: Journal Article
• Language: English
• Published: Hoboken Wiley Subscription Services, Inc., A Wiley Company 2006
• ISSN: 0044-7870; 1550-8390; 1936-1734; 1550-8390
• DOI: 10.1002/meet.14504301228

In this paper, we propose a method that suggests BSH4 (Japan Library Association, 1999) subject headings according to user queries when pattern matching algorithms fail to produce a hit. As user queries are diverse and unpredictable, we explore a method that makes a suggestion even when the query is a new word. We investigate the use of information obtained from Wikipedia (“Wikipedia,” n.d.), the Amazon Web Service (AWS), and Google. We implemented the method, and our system suggests ten BSH4 subject headings according to user queries.