東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back to Search results for [ null ]

Switch To: Labeled | MARC Mode | ISBD

Distributed annotation framework sup...

Imudom, Sukumal.

Linked to FindBook

Google Book

Amazon

博客來

Distributed annotation framework supporting collaborative filtering of information.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Distributed annotation framework supporting collaborative filtering of information./
Author:	Imudom, Sukumal.
Description:	122 p.
Notes:	Adviser: B. Clifford Neuman.
Contained By:	Dissertation Abstracts International63-12B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3073797
ISBN:	9780493939025

Distributed annotation framework supporting collaborative filtering of information.
Imudom, Sukumal.

Distributed annotation framework supporting collaborative filtering of information. - 122 p.

Adviser: B. Clifford Neuman.

Thesis (Ph.D.)--University of Southern California, 2002.

Recommender systems have emerged to assist users by finding information on the Internet with the help of other users. This research proposes a distributed annotation framework supporting collaborative filtering of any type of information. There exists the problem of validity and trust in the recommendations placed on such systems and the lack of incentive for evaluators to participate in making evaluations. The framework provides a mechanism to build trust by increasing the reputation of the evaluators. It also serves as a reward model by providing an incentive for promoting evaluations.

ISBN: 9780493939025Subjects--Topical Terms:

626642
Computer Science.

Distributed annotation framework supporting collaborative filtering of information.
LDR:02881nam 2200277 a 45 001 965915
005 20110908
008 110908s2002 eng d
020 $a 9780493939025
035 $a (UnM)AAI3073797
035 $a AAI3073797
040 $a UnM $c UnM
100 1 $a Imudom, Sukumal. $3 1288665
245 1 0 $a Distributed annotation framework supporting collaborative filtering of information.
300 $a 122 p.
500 $a Adviser: B. Clifford Neuman.
500 $a Source: Dissertation Abstracts International, Volume: 63-12, Section: B, page: 5932.
502 $a Thesis (Ph.D.)--University of Southern California, 2002.
520 $a Recommender systems have emerged to assist users by finding information on the Internet with the help of other users. This research proposes a distributed annotation framework supporting collaborative filtering of any type of information. There exists the problem of validity and trust in the recommendations placed on such systems and the lack of incentive for evaluators to participate in making evaluations. The framework provides a mechanism to build trust by increasing the reputation of the evaluators. It also serves as a reward model by providing an incentive for promoting evaluations.
520 $a The proposed framework consists of three important building blocks which aim to overcome existing recommender system limitations: annotation semantic categories, expertise ratings on the annotators, and a credit mechanism. The framework allows both enumerated and free text forms of evaluation. A generic set of annotation semantic categories is defined to help classify the free text annotations and provide the annotations with structure. The notion of "expertise" is introduced to help identify the experts in our system. The expertise rating mechanism identifying the experts and the quality of evaluations also helps determine the credibility of the information. Additionally, I propose a credit model which overcomes the lack of initial evaluations by providing an incentive to promote user participation. The model, a hybrid of the subscription and transaction models, uses electronic credits as a reward for evaluators who make early and valuable annotations. The framework enables application developers the ability to build various applications which will benefit from collaborative filtering. We envision the future use of these applications in the integration of Recommender Systems and Electronic Commerce. Such systems will not only help users filter the quality of information more efficiently, but it will also provide a new working medium for many career professionals.
590 $a School code: 0208.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 0 $a University of Southern California. $3 700129
773 0 $t Dissertation Abstracts International $g 63-12B.
790 $a 0208
790 1 0 $a Neuman, B. Clifford, $e advisor
791 $a Ph.D.
792 $a 2002
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3073797