{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T21:51:10Z","timestamp":1761947470319,"version":"3.33.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Comput. Sci. Technol."],"published-print":{"date-parts":[[2008,1]]},"DOI":"10.1007\/s11390-008-9115-1","type":"journal-article","created":{"date-parts":[[2008,1,30]],"date-time":"2008-01-30T06:46:30Z","timestamp":1201675590000},"page":"112-128","source":"Crossref","is-referenced-by-count":40,"title":["Clustering Text Data Streams"],"prefix":"10.1007","volume":"23","author":[{"given":"Yu-Bao","family":"Liu","sequence":"first","affiliation":[]},{"given":"Jia-Rong","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Ada Wai-Chee","family":"Fu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2008,1,31]]},"reference":[{"key":"9115_CR1","doi-asserted-by":"crossref","unstructured":"Dou Shen, Qiang Yang, JianTao Sun, Zheng Chen. Thread detection in dynamic text message streams. In Proc. ACM SIGIR 2006, Seattle, Washington, August 6\u201311, pp.35\u201342.","DOI":"10.1145\/1148170.1148180"},{"key":"9115_CR2","doi-asserted-by":"crossref","unstructured":"Aggarwal C C. A framework for diagnosing changes in evolving data streams. In Proc. ACM SIGMOD 2003, San Diego, June 9\u201312, pp.575\u2013586.","DOI":"10.1145\/872757.872826"},{"key":"9115_CR3","doi-asserted-by":"crossref","unstructured":"Agrawal C C, Han J, Wang J, Yu P S. A framework for clustering evolving data streams. In Proc. VLDB 2003, Berlin, September 9\u201312, 2003, pp.81\u201392.","DOI":"10.1016\/B978-012722442-8\/50016-1"},{"key":"9115_CR4","doi-asserted-by":"crossref","unstructured":"Agrawal C C, Han J, Wang J, Yu P S. A framework for projected clustering of high dimensional data streams. In Proc. VLDB 2004, Toronto, August 31-September 3, pp.852\u2013863.","DOI":"10.1016\/B978-012088469-8.50075-9"},{"key":"9115_CR5","doi-asserted-by":"crossref","unstructured":"O\u2019Callaghan L, Mishra N, Meyerson A, Guha S. Streaming data algorithms for high-quality clustering. In Proc. ICDE 2002, San Jose, CA, February 26-March 1, pp.685\u2013704.","DOI":"10.1109\/ICDE.2002.994785"},{"key":"9115_CR6","doi-asserted-by":"crossref","unstructured":"Aggarwal C C, Yu P S, A framework for clustering massive text and categorical data streams. In Proc. SIAM Conference on Data Mining, Bethesda, MD, April 20\u201322, 2006, pp.407\u2013411.","DOI":"10.1137\/1.9781611972764.44"},{"key":"9115_CR7","doi-asserted-by":"crossref","unstructured":"Yang Y, Pierce T, Carbonell J. A study of retrospective and on-line event detection. In Proc. ACM SIGIR, Melbourne, August 24\u201328, 1998, pp.28\u201336.","DOI":"10.1145\/290941.290953"},{"key":"9115_CR8","doi-asserted-by":"crossref","unstructured":"Arindam Banerjee, Sugato Basu. Topic models over text streams: A study of batch and online unsupervised learning. In Proc. SIAM Conference on Data Mining, Minneapolis, April 26\u201328, 2007, pp.437\u2013442.","DOI":"10.1137\/1.9781611972771.40"},{"key":"9115_CR9","doi-asserted-by":"crossref","unstructured":"Xiaodan Zhang, Xiaohua Zhou, Xiaohua Hu. Semantic smoothing for model-based document clustering. In Proc. ICDM06, Hong Kong, December 18\u201322, pp.1193\u20131198.","DOI":"10.1109\/ICDM.2006.142"},{"key":"9115_CR10","doi-asserted-by":"crossref","unstructured":"Zhou X, Hu X, Zhang X, Lin X, Song I Y. Context-sensitive semantic smoothing for the language modeling approach to genomic IR. In Proc. ACM SIGIR, Seattle, Washington, August 6\u201311, 2006, pp.170\u2013177.","DOI":"10.1145\/1148170.1148203"},{"key":"9115_CR11","doi-asserted-by":"crossref","unstructured":"Zhai C, Lafferty J. Two-stage language models for information retrieval. In Proc. ACM SIGIR, Tampere, August 11\u201315, 2002, pp.49\u201356.","DOI":"10.1145\/564376.564387"},{"key":"9115_CR12","doi-asserted-by":"crossref","unstructured":"Zhai C, Lafferty J. A study of smoothing methods for language models applied to ad hoc information retrieval. In Proc. ACM SIGIR, New Orleans, September 9\u201313, 2001, pp.334\u2013342.","DOI":"10.1145\/383952.384019"},{"key":"9115_CR13","doi-asserted-by":"crossref","unstructured":"Yubao Liu, Jiarong Cai, Jian Yin, Ada Wai-Chee Fu. Clustering massive text data streams by semantic smoothing model. In Proc. ADMA, Harbin, August 6\u20138, 2007, pp.389\u2013400.","DOI":"10.1007\/978-3-540-73871-8_36"},{"issue":"3","key":"9115_CR14","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1007\/s10115-004-0194-1","volume":"8","author":"S Zhong","year":"2005","unstructured":"Zhong S, Ghosh J. Generative model-based document clustering: A comparative study. Knowledge and Information Systems, 2005, 8(3): 374\u2013384.","journal-title":"Knowledge and Information Systems"},{"key":"9115_CR15","unstructured":"Steinbach M, Karypis G, Kumar V. A comparison of document clustering techniques. In Proc. Text Mining Workshop, KDD 2000, Boston, August 20\u201323, pp.1\u201320."},{"key":"9115_CR16","doi-asserted-by":"crossref","unstructured":"Guha S, Mishra N, Motwani R, O\u2019Callaghan L. Clustering data streams. In Proc. FOCS 2000, California, November 12\u201314, pp.359\u2013366.","DOI":"10.1109\/SFCS.2000.892124"},{"issue":"5\u20136","key":"9115_CR17","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1016\/j.neunet.2005.06.008","volume":"18","author":"Shi Zhong","year":"2005","unstructured":"Shi Zhong. Efficient streaming text clustering. Neural Networks, 2005, 18(5\u20136): 790\u2013798.","journal-title":"Neural Networks"},{"key":"9115_CR18","unstructured":"Fung G P C, Yu J X, Yu P S, Lu H. Parameter free bursty events detection in text streams. In Proc. VLDB 2005, Trondheim, August 30-September 2, pp.181\u2013192"},{"key":"9115_CR19","doi-asserted-by":"crossref","unstructured":"Qi He, Kuiyu Chang, Ee-Peng Lim, Jun Zhang. Bursty feature representation for clustering text streams. In Proc. SIAM Conference on Data Mining 2007, Minneapolis, April 26\u201328, pp.491\u2013496.","DOI":"10.1137\/1.9781611972771.50"},{"issue":"6","key":"9115_CR20","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1007\/s11390-005-0763-0","volume":"20","author":"Xu-Bin Deng","year":"2005","unstructured":"Xu-Bin Deng, Yang-Yong Zhu. L-tree match: A new data extraction model and algorithm for huge text stream with noises. Journal of Computer Science and Technology, 2005, 20(6): 763\u2013773.","journal-title":"Journal of Computer Science and Technology"},{"key":"9115_CR21","doi-asserted-by":"crossref","unstructured":"Gabriel Pui Cheong Fung, Jeffery Xu Yu, Hongjun Lu. Classifying text streams in the presence of concept drifts. In Proc. PAKDD 2004, Sydney, May 26\u201328, pp.373\u2013383.","DOI":"10.1007\/978-3-540-24775-3_45"},{"key":"9115_CR22","doi-asserted-by":"crossref","unstructured":"Haixun Wang, Jian Yin, Jian Pei, Philip S Yu, Jeffrey Xu Yu. Suppressing model over-fitting in mining concept-drifting data streams. In Proc. KDD 2006, Philadelphia, August 20\u201323, pp.736\u2013741.","DOI":"10.1145\/1150402.1150496"},{"key":"9115_CR23","doi-asserted-by":"crossref","unstructured":"Weiheng Zhu, Jian Pei, Jian Yin, Yihuang Xie. Granularity adaptive density estimation and on demand clustering of concept-drifting data streams. In Proc. DaWaK 2006, Krakow, September 4\u20138, pp.322\u2013331.","DOI":"10.1007\/11823728_31"},{"key":"9115_CR24","unstructured":"Qiaozhu Mei, Chengxiang Zhai. Discovering evolutionary theme patterns from text\u2013An exploration of temporal text mining. In Proc. KDD 2005, Chicago, August 21\u201324, pp.198\u2013207."},{"key":"9115_CR25","doi-asserted-by":"crossref","unstructured":"Shouke Qin, Weining Qian, Aoying Zhou. Approximately processing multi-granularity aggregate queries over data streams. In Proc. ICDE 2006, Atlanta, April 3\u20138, p.67.","DOI":"10.1109\/ICDE.2006.22"},{"issue":"2","key":"9115_CR26","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1007\/s11390-007-9024-8","volume":"22","author":"Dong-Hong Han","year":"2007","unstructured":"Dong-Hong Han, Guo-Ren Wang, Chuan Xiao, Rui Zhou. Load shedding for window joins over streams. Journal of Computer Science and Technology, 2007, 22(2): 182\u2013189.","journal-title":"Journal of Computer Science and Technology"},{"issue":"2","key":"9115_CR27","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1007\/s11390-006-0284-5","volume":"21","author":"Zhi-Hong Chong","year":"2006","unstructured":"Zhi-Hong Chong, Jeffrey Xu Yu, Zhen-Jie Zhang, Xue-Min Lin, Wei Wang, Ao-Ying Zhou. Efficient computation of k-medians over data streams under memory constraints. Journal of Computer Science and Technology, 2006, 21(2): 284\u2013296.","journal-title":"Journal of Computer Science and Technology"},{"key":"9115_CR28","unstructured":"Jian Pei, Haixun Wang, Philip S Yu. Online mining of data streams: Applications, techniques and progress. In Proc. KDD 2004 (Tutorials), Seattle, WA, August 22\u201325, pp.1\u201360."},{"issue":"1","key":"9115_CR29","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/s11390-005-0007-3","volume":"20","author":"Joong Hyuk Chang","year":"2005","unstructured":"Joong Hyuk Chang, Won Suk Lee. Effect of count estimation in finding frequent itemsets over online transactional data streams. Journal of Computer Science and Technology, 2005, 20(1): 63\u201369.","journal-title":"Journal of Computer Science and Technology"},{"issue":"2","key":"9115_CR30","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/s10619-005-3296-1","volume":"18","author":"Jiawei Han","year":"2005","unstructured":"Jiawei Han, Yixin Chen, Guozhu Dong, Jian Pei, Benjamin W Wah, Jianyong Wang, Y Dora Cai. Stream cube: An architecture for multi-dimensional analysis of data streams. Distributed and Parallel Databases, 2005, 18(2): 173\u2013197.","journal-title":"Distributed and Parallel Databases"},{"key":"9115_CR31","doi-asserted-by":"crossref","unstructured":"Yixin Chen, Guozhu Dong, Jiawei Han, Benjamin W Wah, Jianyong Wang. Multi-dimensional regression analysis of time-series data streams. In Proc. VLDB 2002, August 20\u201323, Hong Kong, pp.323\u2013334.","DOI":"10.1016\/B978-155860869-6\/50036-6"},{"key":"9115_CR32","doi-asserted-by":"crossref","unstructured":"Yubao Liu, Jiarong Cai, Jian Yin, Zhilan Huang. Document clustering based on semantic smoothing approach. In Proc. AWIC 2007, Fontainebleau, June 25\u201327, pp.217\u2013222.","DOI":"10.1007\/978-3-540-72575-6_35"}],"container-title":["Journal of Computer Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-008-9115-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11390-008-9115-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-008-9115-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,26]],"date-time":"2025-01-26T11:46:21Z","timestamp":1737891981000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11390-008-9115-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,1]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2008,1]]}},"alternative-id":["9115"],"URL":"https:\/\/doi.org\/10.1007\/s11390-008-9115-1","relation":{},"ISSN":["1000-9000","1860-4749"],"issn-type":[{"type":"print","value":"1000-9000"},{"type":"electronic","value":"1860-4749"}],"subject":[],"published":{"date-parts":[[2008,1]]}}}