Mining XML data: A clustering approach

XML data has become very popular to represent semi structured data. This has resulted in a growing amount of XML data on the web. This raises a need for languages and tools to manage collections of XML documents as well as to mine interesting information from them. Several attempts at developing XML mining techniques have been proposed. However the topic of mining XML data has received little attention as the data mining community has focused on the development of techniques for extracting common structure from heterogeneous XML data. This project aims to data mine XML data using the XML Query language XQuery. The data mining technique used is the clustering technique of the Nearest Neighbour Algorithm. This algorithm will be incorporated into XQuery expression which, when implemented using an XQuery implementation tool, will cluster distance based data within the XML document into groups, where the distance between the data is set by a given threshold. The implementation of the Nearest Neighbour algorithm hopes to be generic and implement a user interface which allows the user to load a XML document for its data to be clustered, choose the data to be clustered within that document, input the threshold and receive the clustered result in an output file. This work would allow XML distance data to be clustered with the Nearest Neighbour algorithm using XQuery, therefore providing a needed data mining implementation on XML data.