Survey of Text Clustering

Clustering text documents into different category groups is an important step in indexing, retrieval, management and mining of abundant text data on the Web or in corporate information systems. Text clustering task can be intuitively described as finding, given a set vectors of some data points in a multi-dimensional space, a partition of text data into clusters such that the points within each cluster are similar to each other. Good text clustering enables better information services by browsing and organizing documents into meaningful cluster hierarchies and provides a useful complement for traditional text search engines when key-word based search returns too many documents. Among others, the challenging problems of text clustering are big volume, high dimensionality and complex semantics. In this paper we are interested in the solutions to these problems. For the first two problems, subspace clustering can provide bright future, ontology can provide promising solution to the third one.