[1] Lu Jianjiang, Xu Baowen, Huang Gangshi, et al. Matrix dimensionality reduction for mining typical user profiles [J]. Journal of Southeast University (English Edition), 2003, 19 (3): 231-235. [doi:10.3969/j.issn.1003-7985.2003.03.006]

Copy

Matrix dimensionality reduction for mining typical user profiles()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

19

Issue:

2003 3

Page:

231-235

Research Field:

Automation

Publishing date:

2003-09-30

Info

Title:

Matrix dimensionality reduction for mining typical user profiles

Author(s):

Lu Jianjiang¹;  2;  Xu Baowen¹;  3;  Huang Gangshi²;  Zhang Yafei²

¹Department of Computer Science and Engineering, Southeast University, Nanjing 210096, China
²School of Science, PLA University of Science and Technology, Nanjing 210007, China
³School of Computer Science, National

Keywords:

Web usage mining;  non-negative matrix factorization;  spherical k-means algorithm

PACS:

TP18

DOI:

10.3969/j.issn.1003-7985.2003.03.006

Abstract:

Recently clustering techniques have been used to automatically discover typical user profiles. In general, it is a challenging problem to design effective similarity measure between the session vectors which are usually high-dimensional and sparse. Two approaches for mining typical user profiles, based on matrix dimensionality reduction, are presented. In these approaches, non-negative matrix factorization is applied to reduce dimensionality of the session-URL matrix, and the projecting vectors of the user-session vectors are clustered into typical user-session profiles using the spherical k-means algorithm. The results show that two algorithms are successful in mining many typical user profiles in the user sessions.

References:

[1] Konstan J, Miller B, Maltz D. et al. GroupLens: applying collaborative filtering to usenet news [J]. Communications of the ACM, 1997, 40(3): 77-87.
[2] Cooley R, Mobasher B, Srivastava J. Web mining: Information and pattern discovery on the World Wide Web [A]. In: Proc IEEE Intl Conf Tools with AI [C]. Newport Beach, CA, 1997. 558-567.
[3] Chen M S, Park J S, Yu P S. Efficient data mining for path traversal patterns [J]. IEEE Trans on Knowledge and Data Engineering, 1998, 10(2): 209-221.
[4] Nasraoui O, Frigui H, Krishnapuram R. et al. Extracting Web user profiles using relational competitive fuzzy clustering [J]. International Journal on Artifical Intelligence Tools, 2000, 9(4): 509-526.
[5] Nasraoui O, Krishnapuram R, Joshi A. Mining Web access logs using relational clustering algorithm based on a robust estimator [A]. In: NAFIPS Conference [C]. New York, NY, 1999.705-709.
[6] Nasraoui O, Krishnapuram R. One step evolutionary mining of context sensitive associations and Web navigation patterns [A]. In: Second SIAM International Conference on Data Mining [C]. Arlington, VA, 2002. 531-547.
[7] Hinneburg A, Aggarwal C C, Keim D A. What is the nearest neighbor in high dimensional spaces? [A]. In: Proceedings of the VLDB Conference [C]. Cario, Egypt, 2000. 506-515.
[8] Lee D, Seung H. Learning the parts of objects by non-negative matrix factorization [J]. Nature, 1999, 401:788-791.
[9] Lee D, Seung H. Algorithms for non-negative matrix factorization [A]. In:Adv Neural Info Proc Syst[C]. 2001, 13:556-562.
[10] Li S Z, Hou X W, Zhang H J. Learning spatially localized parts-based representation [A]. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition [C]. Hawaii, 2001. 207-212.
[11] Mobasher B, Jain N, Han E-H. et al. Web mining [R]. U. of Minnesota, 1996.
[12] Inderjit S D, Dharmendra S M. Concept decompositions for large sparse text using clustering [J]. Machine Learning, 2001, 42(1): 143-175.

Memo

Memo:

Biographies: Lu Jianjiang(1968—), male, associate professor; Xu Baowen(corresponding author), male, doctor, professor, bwxu@seu.edu.cn.

Common functions