{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T07:37:36Z","timestamp":1742801856520,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,11]]},"DOI":"10.1109\/cbd.2014.56","type":"proceedings-article","created":{"date-parts":[[2015,8,13]],"date-time":"2015-08-13T18:52:55Z","timestamp":1439491975000},"page":"18-25","source":"Crossref","is-referenced-by-count":4,"title":["Scaling Information-Theoretic Text Clustering: A Sampling-based Approximate Method"],"prefix":"10.1109","author":[{"given":"Zhexi","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengnong","family":"Xuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2004.1381996"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2007.59"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1023\/A:1014056429969","article-title":"On issues of instance selection","volume":"6","author":"huan","year":"2002","journal-title":"Data Mining and Knowledge Discovery"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511779398"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177732503"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/280765.280872"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_20"},{"key":"ref17","first-page":"105","article-title":"Probabilistic dyadic data analysis with local and global consistency","author":"deng","year":"2009","journal-title":"Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)"},{"key":"ref18","first-page":"311","article-title":"Criterion functions for document clustering: Experiments and analysis","volume":"55","author":"zhao","year":"2004","journal-title":"ML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-004-0194-1"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","article-title":"Independent component analysis:algorithms and applications","volume":"13","year":"2000","journal-title":"Neural Networks"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1454008.1454048"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/276304.276314"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557767"},{"key":"ref6","first-page":"1265","article-title":"A divisive information-theoretic feature clustering algorithm for text classification","volume":"3","author":"dhillon","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","first-page":"298","article-title":"Random projections for k-means clustering","author":"boutsidis","year":"2010","journal-title":"Proceedings of the 2010 Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1298306.1298309"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2212430"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"journal-title":"Search Engines Information Retrieval in Practice","year":"2010","author":"croft","key":"ref2"},{"journal-title":"Proceedings of the World Congress on Engineering and Computer Science 2012","article-title":"Knowledge discovery (email harvesting, gender identification, prediction) in social network data (facebook 100 million url)","year":"2012","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3223-4"},{"key":"ref20","first-page":"1799","article-title":"A theoretic framework of k-means-based consensus clustering","author":"wu","year":"2013","journal-title":"Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-010-9165-y"},{"journal-title":"Algorithms for clustering data","year":"1988","author":"jain","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37807-2_3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-012-0507-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020995206763"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-010-0375-z"}],"event":{"name":"2014 Second International Conference on Advanced Cloud and Big Data (CBD)","start":{"date-parts":[[2014,11,20]]},"location":"Huangshan, China","end":{"date-parts":[[2014,11,22]]}},"container-title":["2014 Second International Conference on Advanced Cloud and Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7077868\/7176054\/07176067.pdf?arnumber=7176067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T13:37:32Z","timestamp":1498225052000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7176067\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,11]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/cbd.2014.56","relation":{},"subject":[],"published":{"date-parts":[[2014,11]]}}}