DocumentCode :
2910292
Title :
Engene: A genetic algorithm classifier for content-based recommender systems that does not require continuous user feedback
Author :
Pagonis, John ; Clark, Adrian F.
Author_Institution :
Pragmaticomm Ltd., Hemel Hempstead, UK
fYear :
2010
fDate :
8-10 Sept. 2010
Firstpage :
1
Lastpage :
6
Abstract :
We present Engene, a genetic algorithm based classifier which is designed for use in content-based recommender systems. Once bootstrapped Engene does not need any human feedback. Although it is primarily used as an on-line classifier, in this paper we present its use as a one-class document batch classifier and compare its performance against that of a one-class k-NN classifier.
Keywords :
content-based retrieval; genetic algorithms; pattern classification; recommender systems; text analysis; bootstrapped Engene; content-based recommender system; genetic algorithm classifier; one-class document batch classifier; online classifier; textual content classifier; user feedback; Gallium; Variable speed drives;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence (UKCI), 2010 UK Workshop on
Conference_Location :
Colchester
Print_ISBN :
978-1-4244-8774-5
Electronic_ISBN :
978-1-4244-8773-8
Type :
conf
DOI :
10.1109/UKCI.2010.5625594
Filename :
5625594
Link To Document :
بازگشت