DocumentCode :
2702941
Title :
Research of reading content recommendation based on behavior mining
Author :
Li, Qing-Cheng ; Dong, Zhen-Hua ; Lin, Shan ; Liu, Jia-xin
Author_Institution :
Dept. of Inf. Tech. Sci., Nankai Univ., Tianjin
fYear :
2008
fDate :
20-23 June 2008
Firstpage :
1717
Lastpage :
1722
Abstract :
It is more and more difficult to find proper information for people in modern knowledge explosion society. Information recommendation systems can reduce information overload and provide appropriate content to targeted user. This paper proposes a new personalized recommendation technique based on mining the userpsilas reading behavior through 5W1H scheme. By comparing the user profile and the information representation, we can recommend the customized content in suitable time to satisfy the userpsilas personalized requirement. For performance evaluation, we implement the service to make experiments on real information and people. The results show that our technology and approach can acquire the userpsilas reading requirement, and recommend suitable information they really need.
Keywords :
data mining; information filtering; information filters; 5W1H scheme; customized content; information overload; information recommendation system; information representation; personalized recommendation technique; reading content recommendation; user personalized requirement; user profile; user reading behavior mining; Automation; Computer architecture; Data mining; Dictionaries; Explosions; Information filtering; Information representation; Information retrieval; Search engines; Software performance;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information and Automation, 2008. ICIA 2008. International Conference on
Conference_Location :
Changsha
Print_ISBN :
978-1-4244-2183-1
Electronic_ISBN :
978-1-4244-2184-8
Type :
conf
DOI :
10.1109/ICINFA.2008.4608282
Filename :
4608282
Link To Document :
بازگشت