Concept decompositions for large sparse text data using clustering

@article{citeulike:478824, abstract = {Unstructured text documents are becoming increasingly common and available; mining such data sets represents a major contemporary challenge. Using words as features, text documents are often represented as high-dimensional and sparse vectors--a few thousand dimensions and a sparsity of 95 to 99\% is typical. In this paper, we study a certain spherical k-means algorithm for clustering such document vectors. The algorithm outputs k disjoint clusters each with a concept vector that is the centroid...}, author = {Dhillon, I. S. and Modha, D. S. }, citeulike-article-id = {478824}, journal = {Machine Learning}, keywords = {concept, decomposition, k-means, spherical}, number = {1}, pages = {143--175}, posted-at = {2006-06-09 23:55:29}, priority = {0}, title = {Concept decompositions for large sparse text data using clustering}, url = {http://citeseer.ist.psu.edu/405289.html}, volume = {42}, year = {2001} }

TY - JOUR ID - citeulike:478824 L3 - citeulike-article-id:478824 TI - Concept decompositions for large sparse text data using clustering JF - Machine Learning VL - 42 IS - 1 SP - 143 EP - 175 N2 - Unstructured text documents are becoming increasingly common and available; mining such data sets represents a major contemporary challenge. Using words as features, text documents are often represented as high-dimensional and sparse vectors--a few thousand dimensions and a sparsity of 95 to 99% is typical. In this paper, we study a certain spherical k-means algorithm for clustering such document vectors. The algorithm outputs k disjoint clusters each with a concept vector that is the centroid... KW - concept KW - decomposition KW - k-means KW - spherical AU - Dhillon, IS AU - Modha, DS PY - 2001/// UR - http://citeseer.ist.psu.edu/405289.html ER -