Improving annotation categorization performance through integrated social annotation computation

NCUIR > College of Electrical Engineering & Computer Science > Department of Computer Science and information Engineering > journal & Dissertation > Item 987654321/51548

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/51548

Title:	Improving annotation categorization performance through integrated social annotation computation
Authors:	Su,AYS;Yang,SJH
Contributors:	資訊工程學系
Keywords:	TEXT CATEGORIZATION
Date:	2010
Issue Date:	2012-03-27 18:55:56 (UTC+8)
Publisher:	國立中央大學
Abstract:	People can identify and organize their ideas and comments with respect to relevant concept topics through using annotation systems. Those annotation systems are obvious that only supports a simple and manual categorization approach. The manual approach is a difficult and time-consuming task for general annotators. Therefore, we propose a requirement annotation categorization which helps annotators to promote the manual annotation categorization effectiveness. Moreover, we propose an integrated social annotation computation which improves the performance of our annotation categorization. In summary, the proposed annotation categorization is verified through experiments using real users' data sets. We achieved the 83.11% average accuracy for the proposed annotation categorization with integrated social annotation computation. We also show that the proposed annotation categorization requires only 17-20% average processing time (in comparison with the manual approach) is efficient. (C) 2010 Elsevier Ltd. All rights reserved.
Relation:	EXPERT SYSTEMS WITH APPLICATIONS
Appears in Collections:	[Department of Computer Science and information Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	401	View/Open

社群 sharing