Integrating data and text mining processes for digital library applications Export

@inproceedings{citeulike:1438389, abstract = {This paper explores the integration of text mining and data mining techniques, digital library systems, and computational and data grid technologies with the objective of developing an online classification service exemplar. We discuss the current research issues relating to the use of data mining algorithms and toolkits for textual data; the necessary changes within the Cheshire3 Information Framework to accommodate analysis workflows; the outcomes of a demonstrator based on the National Library of Medicine's Medline dataset; and the provision of comparable metrics for evaluation purposes. The prototype has resulted in extremely accurate online classification services and offers a novel method of supporting text mining and data mining within a highly scaled computational environment, integrated seamlessly into the digital library architecture.}, address = {New York, NY, USA}, author = {Sanderson, Robert and Watry, Paul}, booktitle = {JCDL '07: Proceedings of the 2007 conference on Digital libraries}, citeulike-article-id = {1438389}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1255175.1255188}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1255175.1255188}, doi = {10.1145/1255175.1255188}, isbn = {9781595936448}, keywords = {cheshire\_dl, data\_grid, digital\_library\_architectures, text\_mining}, pages = {73--79}, posted-at = {2007-07-05 23:12:07}, priority = {3}, publisher = {ACM Press}, title = {Integrating data and text mining processes for digital library applications}, url = {http://dx.doi.org/10.1145/1255175.1255188}, year = {2007} }

TY - CONF ID - citeulike:1438389 L3 - citeulike-article-id:1438389 N2 - This paper explores the integration of text mining and data mining techniques, digital library systems, and computational and data grid technologies with the objective of developing an online classification service exemplar. We discuss the current research issues relating to the use of data mining algorithms and toolkits for textual data; the necessary changes within the Cheshire3 Information Framework to accommodate analysis workflows; the outcomes of a demonstrator based on the National Library of Medicine's Medline dataset; and the provision of comparable metrics for evaluation purposes. The prototype has resulted in extremely accurate online classification services and offers a novel method of supporting text mining and data mining within a highly scaled computational environment, integrated seamlessly into the digital library architecture. SN - 9781595936448 AD - New York, NY, USA EP - 79 TI - Integrating data and text mining processes for digital library applications PB - ACM Press T2 - JCDL '07: Proceedings of the 2007 conference on Digital libraries SP - 73 KW - cheshire_dl KW - data_grid KW - digital_library_architectures KW - text_mining AU - Sanderson, Robert AU - Watry, Paul PY - 2007/// UR - http://dx.doi.org/10.1145/1255175.1255188 ER -