“Data Mining for XML Query- Answering Support using feeds”

Abstract? The enormous amount of internet causes huge amount of data to be stored and processed which contains structured and semi structured formats. Due to extreme size of semi structured document, results of a particular query may be vast which leads to retrieving interpretable knowledge a tedious process. The query-answering system makes it achievable to make queries and retrieve results for XML documents and reduce processing of tremendous size data.. In this project, we propose a method for retrieving more efficient more accurate results for the queries made by the users on the XML document. The original XML document is translated to Tree based association rules (TAR) files which were formed by frequent patterns on the original document. TAR files provide intensional information on the structure and content of XML document. Also we are using CMTree Miner algorithm to mine most frequent set of xml sub-trees, and also comparing CM Tree miner or alternative algorithm with existing XML frequent pattern miner approaches.