Extended VSM for XML Document Classification Using Frequent Subtrees

Structured link vector model (SLVM) is a representation proposed for modeling XML documents which was extended from the conventional vector space model (VSM) by incorporating document structures In this paper we describe the classification approach for XML documents based on SLVM in the Document Mining Challenge of INEX 2009 where the closed frequent subtrees as structural units are used for content extraction from the XML document and the Chi-square test is used for feature selectionComputer Science, Information SystemsComputer Science, Software EngineeringComputer Science, Theory & MethodsEICPCI-S(ISTP)