Frequent term-based text clustering

摘要: Text clustering methods can be used to structure large sets of text or hypertext documents. The well-known clustering, however, do not really address the special problems clustering: very high dimensionality data, size databases and understandability cluster description. In this paper, we introduce a novel approach which uses frequent item (term) for clustering. Such efficiently discovered using algorithms association rule mining. To based on term sets, measure mutual overlap with respect supporting We present two term-based FTC creates flat clusterings HFTC hierarchical An experimental evaluation classical documents as well web demonstrates that proposed obtain comparable quality significantly more than state-of-the- art algorithms. Furthermore, our provide an understandable description clusters by their sets.