Experimental study on the extraction and distribution of textual domain keywords
Authors:
- 31 March 2008
- journal article
- research article
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 20 (16) , 1917-1932
Abstract
Domain keywords of text play a primary role in text classifying, clustering and personalized services. This paper proposes a term frequency inverse document frequency (TFIDF) based method called TDDF (TFIDF direct document frequency of domain) to extract domain keywords from multi‐texts. First, we discuss the optimal parameters of TFIDF, which are used to extract textual keywords and domain keywords. Second, TDDF is proposed to extract domain keywords from multi‐texts, which takes document frequency of domain into account. Finally, the distribution of domain keywords on scientific texts is studied. Experiments and applications show that TDDF is more effective than the optimal TFIDF in the extraction of domain keywords. Domain keywords accord with normal distribution on a single text after deleting the ubiquitous domain keywords. Copyright © 2008 John Wiley & Sons, Ltd.Keywords
This publication has 9 references indexed in Scilit:
- Automatic generation of document semantics for the e-science Knowledge GridJournal of Systems and Software, 2006
- Learning with an active e‐course in the Knowledge Grid environmentConcurrency and Computation: Practice and Experience, 2005
- Knowledge Map: Mathematical Model and Dynamic BehaviorsJournal of Computer Science and Technology, 2005
- Machine learning in automated text categorizationACM Computing Surveys, 2002
- 10.1162/jmlr.2003.3.4-5.993Applied Physics Letters, 2000
- Inductive learning algorithms and representations for text categorization1998
- Automatic essay grading using text categorization techniques1998
- Feature selection, perception learning, and a usability case study for text categorization1997
- ON THE SPECIFICATION OF TERM VALUES IN AUTOMATIC INDEXINGJournal of Documentation, 1973