Please use this identifier to cite or link to this item:
Title: Learning and reasoning on background net - its application to text categorization
Authors: Lo, S.-L.
Ding, L. 
Keywords: Background net
Incremental learning
Personalized article selection
Similarity and acceptance measure
Text categorization
Issue Date: Mar-2012
Citation: Lo, S.-L.,Ding, L. (2012-03). Learning and reasoning on background net - its application to text categorization. ICIC Express Letters 6 (3) : 625-631. ScholarBank@NUS Repository.
Abstract: This article proposes a novel approach for text categorization, using knowledge background accumulated through incremental learning on articles. The background information is represented as weighted undirected graph called background net that captures the contextual association of terms appeared in the articles recommended. With such a background net constructed, the understanding of a term is achieved using a fuzzy set based on contextual association of the given term to other terms involved in the back-ground net. The acceptance measures are defined to evaluate candidate article through the reasoning on background net. This approach applies not only to text categorization but also to personalized articles selection. © 2012 ICIC International.
Source Title: ICIC Express Letters
ISSN: 1881803X
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

checked on Oct 14, 2021

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.