Volume 28, Issue 2 (3-2013)                   ... 2013, 28(2): 411-432 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Kermani A, Neshat N, Horri A. Application of Bibliographic Coupling versus Cited Titles Words in Patent Fuzzy Clustering . .... 2013; 28 (2) :411-432
URL: http://jipm.irandoc.ac.ir/article-1-1935-en.html
Abstract:   (8304 Views)
Attribute selection is one of the steps before patent clustering. Various attributes can be used for clustering. In this study, the effect of using citation and citation title words, respectively, in form of bibliographic coupling and citation title words sharing, were measured and compared with each other, as patent attributes. This study was done in an experimental method, on a collection of 717 US Patent cited in the patents belong to 977/774 subclass of US Patent Classification. Fuzzy C-means was used for patent clustering and extended BCubed precision and extended BCubed recall were used as evaluation measure. The results showed that the clustering produced by bibliographic coupling had better performance than clustering used citation title words and existence of cluster structure were in a wider range of exhaustivity than citation title words.
Full-Text [PDF 796 kb]   (1930 Downloads)    
Type of Study: Research | Subject: Library and Information Science
Received: 2012/05/27

Add your comments about this article : Your username or Email:
CAPTCHA code

Send email to the article author


© 2019 All Rights Reserved | Iranian Journal of Information processing and Management

Designed & Developed by : Yektaweb