DocumentCode
2295708
Title
A probabilistic information filtering using the profile dynamics
Author
Barbu, Costin ; Simina, Marin
Author_Institution
Dept. of Electr. Eng. & Comput. Sci., Tulane Univ., New Orleans, LA, USA
Volume
5
fYear
2003
fDate
5-8 Oct. 2003
Firstpage
4595
Abstract
This paper presents an algorithm for learning incrementally the profile of a user, based on an (optional) initial user profile and on user´s queries using probabilistic latent semantic analysis. A new model, a temporal latent semantic space, is introduced in order to keep track of the user´s interests´ changes. The results of the retrieval experiments using this new algorithm are compared with other traditional information retrieval techniques.
Keywords
information filters; information retrieval; learning (artificial intelligence); probability; information retrieval techniques; probabilistic information filtering; probabilistic latent semantic analysis; profile dynamics; temporal latent semantic space; user profile; Adaptive algorithm; Algorithm design and analysis; Filtering algorithms; Indexing; Information analysis; Information filtering; Information filters; Information retrieval; Search engines; World Wide Web;
fLanguage
English
Publisher
ieee
Conference_Titel
Systems, Man and Cybernetics, 2003. IEEE International Conference on
ISSN
1062-922X
Print_ISBN
0-7803-7952-7
Type
conf
DOI
10.1109/ICSMC.2003.1245708
Filename
1245708
Link To Document