A methodology for clustering XML documents by structure Export

@article{citeulike:5406012, abstract = {The processing and management of XML data are popular research issues. However, operations based on the structure of XML data have not received strong attention. These operations involve, among others, the grouping of structurally similar XML documents. Such grouping results from the application of clustering methods with distances that estimate the similarity between tree structures. This paper presents a framework for clustering XML documents by structure. Modeling the XML documents as rooted ordered labeled trees, we study the usage of structural distance metrics in hierarchical clustering algorithms to detect groups of structurally similar XML documents. We suggest the usage of structural summaries for trees to improve the performance of the distance calculation and at the same time to maintain or even improve its quality. Our approach is tested using a prototype testbed.}, author = {Dalamagas, Theodore and Cheng, Tao and Winkel, Klaas-Jan and Sellis, Timos}, citeulike-article-id = {5406012}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.5394}, journal = {Information Systems}, keywords = {clustering, structure, tree, xml}, pages = {187--228}, posted-at = {2009-08-10 21:09:17}, priority = {2}, title = {A methodology for clustering XML documents by structure}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.5394}, volume = {31}, year = {2006} }

TY - JOUR ID - citeulike:5406012 L3 - citeulike-article-id:5406012 N2 - The processing and management of XML data are popular research issues. However, operations based on the structure of XML data have not received strong attention. These operations involve, among others, the grouping of structurally similar XML documents. Such grouping results from the application of clustering methods with distances that estimate the similarity between tree structures. This paper presents a framework for clustering XML documents by structure. Modeling the XML documents as rooted ordered labeled trees, we study the usage of structural distance metrics in hierarchical clustering algorithms to detect groups of structurally similar XML documents. We suggest the usage of structural summaries for trees to improve the performance of the distance calculation and at the same time to maintain or even improve its quality. Our approach is tested using a prototype testbed. JF - Information Systems EP - 228 TI - A methodology for clustering XML documents by structure VL - 31 SP - 187 KW - clustering KW - structure KW - tree KW - xml AU - Dalamagas, Theodore AU - Cheng, Tao AU - Winkel, Klaas-Jan AU - Sellis, Timos PY - 2006/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.5394 ER -