Obtaining profiles based on localized non-negative matrix factorization
Web Information Mining and Retrieval
Received:
- 26 Downloads
Abstract
Nonnegative matrix factorization (NMF) is a method to get parts-based features of information and form the typical profiles. But the basis vectors NMF gets are not orthogonal so that parts-based features of information are usually redundancy. In this paper, we propose two different approaches based on localized non-negative matrix factorization (LNMF) to obtain the typical user session profiles and typical semantic profiles of junk mails. The LNMF get basis vectors as orthogonal as possible so that it can get accurate profiles. The experiments show that the approach based on LNMF can obtain better profiles than the approach based on NMF.
Key words
localized non-negative matrix factorization profile log mining mail filteringCLC number
TP 391 Download
to read the full article text
References
- [1]Lu Jian-jiang, Xu Bao-wen, Yang Hong-ji. Matrix dimensionality reduction for mining Web access logs.Proceedings of IEEE/WIC International Conference on Web Intelligence, Halifax, CA, 2003. 405–408.Google Scholar
- [2]Soonthornphisaj N, Chaikulseriwat K, Tang-on P. Anti-Spam Filtering: A Centroid-based Classification Approach.Proceedings of the International. Conference on Signal Processing, Beijing, 2002. 1096–1099.Google Scholar
- [3]Guillamet D, Schiele B. Analyzing nonnegative matrix factorization for image classification.Proceedings of International Conference in Pattern Recognition, Quebec City, 2002. 116–119.Google Scholar
- [4]Xu Bao-wen, Lu Jian-jiang, Huang Gang-shi. A constrained non-negative matrix factorization in information retrieval.The 2003 IEEE International Conference on Information Reuse and Integration. Nevada, USA. 2003. 273–277.Google Scholar
- [5]Lee D D, Seung H S. Learning the parts of objects by nonnegative matrix factorization.Nature, 1999,401: 788–791.CrossRefGoogle Scholar
- [6]Li S Z, Hou Xin-wen, Zhang Hong-Jiang. Learning spatially localized parts-based representation.Proceedings of the CVPR’01 Conference, Hawaii, USA, 2001, 207–212.Google Scholar
- [7]Yart T W, Garcia-Molina H. Index Structures for Information Filtering under the Vector Space Model.Proceedings of the 10th International Conference on Data Engineering, Alamitos, CA, 1994. 337–347.Google Scholar
- [8]Sebastiani F. Machine learning in automated text categorization.ACM Computing Surveys, 2002,34(1): 1–47.CrossRefGoogle Scholar
- [9]Inderjit S D, Dharmendra S M. Concept decompositions for large sparse text using clustering.Machine Learning, 2001,42(1): 143–175.MATHCrossRefGoogle Scholar
Copyright information
© Springer 2004