{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T12:17:59Z","timestamp":1763036279741},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007,4]]},"DOI":"10.1109\/icdew.2007.4401066","type":"proceedings-article","created":{"date-parts":[[2007,12,18]],"date-time":"2007-12-18T19:56:26Z","timestamp":1198007786000},"page":"770-779","source":"Crossref","is-referenced-by-count":25,"title":["Document Representation and Dimension Reduction for Text Clustering"],"prefix":"10.1109","author":[{"given":"Mahdi","family":"Shafiei","sequence":"first","affiliation":[]},{"given":"Singer","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Roger","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Evangelos","family":"Milios","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Jane","family":"Tougas","sequence":"additional","affiliation":[]},{"given":"Ray","family":"Spiteri","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Perl package Text Ngrams","year":"0","author":"keselj","key":"ref10"},{"key":"ref11","article-title":"N-gram-based author profiles for authorship attribution","author":"keselj","year":"2003","journal-title":"Proc Pacific Association Computational Linguistics Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-0443-8_13"},{"article-title":"Document clustering in reduced dimension vector space","year":"1999","author":"lerman","key":"ref13"},{"journal-title":"Comparing document clusteing using n-grams words and terms","year":"2004","author":"mao","key":"ref14"},{"key":"ref15","first-page":"60","article-title":"Term-based clustering and summarization of web page collections","author":"milios","year":"2004","journal-title":"the Seventeenth Conference of the Canadian Society for Computational Studies of Intelligence (AI04)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007731"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/215206.215365"},{"key":"ref19","article-title":"A systematic study of document representation and dimension reduction for text clustering","author":"shafiei","year":"2006","journal-title":"Technical Report Technical Report CS-2006-05 Faculty of Computer Science"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/956755.956764"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012801612483"},{"key":"ref5","article-title":"A survey of dimension reduction techniques","author":"fodor","year":"2002","journal-title":"Technical Report UCRL-ID-148494 Center for Applied Scientific Computing Lawrence Livermore National Laboratory"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/72.761722"},{"key":"ref7","first-page":"145","article-title":"On the use of the singular value decomposition for text retrieval","author":"husbands","year":"2001","journal-title":"Computational Information Retrieval"},{"key":"ref2","first-page":"269","article-title":"Using an n-gram-based document representation with a vector processing retrieval model","author":"cavnar","year":"1994","journal-title":"TREC"},{"key":"ref9","article-title":"An introduction to a new data analysis tool: Independent component analysis","author":"jung","year":"2001","journal-title":"Proceedings of Workshop GK &#x201C;Nonlinearity&#x201D;"},{"key":"ref1","first-page":"217","article-title":"When is the nearest neighbour meaningful?","author":"beyer","year":"1999","journal-title":"Proceedings of the 7th International Conference on Database Theory"},{"key":"ref20","article-title":"A comparison of common document clustering techniques","author":"steinbach","year":"2000","journal-title":"KDD Workshop on Text Mining"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/160688.160691"},{"key":"ref21","article-title":"Comparative study of dimension reduction techniques for document clustering","author":"tang","year":"2004","journal-title":"Technical Report CS-2004-14"},{"key":"ref24","first-page":"412","article-title":"A comparative study on feature selection in text categorization","author":"yang","year":"1997","journal-title":"Proceedings of ICML-97 14th International Conference on Machine Learning"},{"key":"ref23","article-title":"Kmeans clustering versus validation measures a data distribution perspective","author":"xiong","year":"2006","journal-title":"KDD"},{"key":"ref26","article-title":"Criterion functions for document clustering: Experiments and analysis","author":"zhao","year":"2001","journal-title":"Technical Report TR #01-40"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/17.9.763"}],"event":{"name":"2007 IEEE 23rd International Conference on Data Engineering Workshop","start":{"date-parts":[[2007,4,17]]},"location":"Istanbul, Turkey","end":{"date-parts":[[2007,4,20]]}},"container-title":["2007 IEEE 23rd International Conference on Data Engineering Workshop"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4400942\/4400943\/04401066.pdf?arnumber=4401066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T19:55:58Z","timestamp":1489694158000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4401066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icdew.2007.4401066","relation":{},"subject":[],"published":{"date-parts":[[2007,4]]}}}