Skip to Main Content
With the increase of XML data over the Internet, managing and analyzing huge amount of XML documents has played an important role for information management. This paper addresses the problem of clustering XML documents. Borrowing the idea of semi-clustering, it proposes a robust clustering method through a combination of single partitional and hierarchical clustering algorithms, which can eliminate the defects of single clustering algorithms. Experiments on real XML documents collection show that our method can group large collection of XML documents into appropriate clusters efficiently without fixed number of clusters. Moreover, our method is less sensitive to noises than single clustering algorithm.