{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:25:08Z","timestamp":1743060308214,"version":"3.40.3"},"publisher-location":"Boston, MA","reference-count":43,"publisher":"Springer US","isbn-type":[{"type":"print","value":"9780387098227"},{"type":"electronic","value":"9780387098234"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-0-387-09823-4_48","type":"book-chapter","created":{"date-parts":[[2010,9,9]],"date-time":"2010-09-09T15:02:00Z","timestamp":1284044520000},"page":"931-948","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Review of Web Document Clustering Approaches"],"prefix":"10.1007","author":[{"given":"Nora","family":"Oikonomakou","sequence":"first","affiliation":[]},{"given":"Michalis","family":"Vazirgiannis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,7,7]]},"reference":[{"key":"48_CR01","unstructured":"Bezdek, J.C., Ehrlich, R., Full, W. FCM: Fuzzy C-Means Algorithm. Computers and Geosciences, 1984."},{"issue":"3","key":"48_CR02","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/S0167-9236(99)00055-X","volume":"27","author":"D. Boley","year":"1999","unstructured":"Boley, D., Gini, M., Gross, R., Han, E.H., Hastings, K., Karypis, G., Kumar, V., Mobasher, B., Moore, J. Partitioning-based clustering for web document categorization. Decision Support Systems, 27(3):329-341, 1999.","journal-title":"Decision Support Systems"},{"key":"48_CR03","doi-asserted-by":"crossref","unstructured":"Botafogo, R.A., Shneiderman, B. Identifying aggregates in hypertext structures. Proc. 3rd ACM Conference on Hypertext, pp.63-74, 1991.","DOI":"10.1145\/122974.122981"},{"key":"48_CR04","doi-asserted-by":"crossref","unstructured":"Botafogo, R.A. Cluster analysis for hypertext systems. Proc. ACM SIGIR Conference on Research and Development in Information Retrieval, pp.116- 125, 1993.","DOI":"10.1145\/160688.160704"},{"key":"48_CR05","unstructured":"Cheeseman, P., Stutz, J. Bayesian Classification (AutoClass): Theory and Results. Advances in Knowledge Discovery and Data Mining, AAAI\/MIT Press, pp. 153-180, 1996."},{"key":"48_CR06","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/0306-4573(93)90058-L","volume":"29","author":"W. B. Croft","year":"1993","unstructured":"Croft, W. B. Retrieval strategies for hypertext. Information Processing and Management, 29:313-324, 1993.","journal-title":"Information Processing and Management"},{"key":"48_CR07","doi-asserted-by":"crossref","unstructured":"Cutting, D.R., Karger, D.R., Pedersen, J.O., Tukey, J.W. Scatter\/Gather: A Cluster-based Approach to Browsing Large Document Collections. Proc. ACM SIGIR Conference on Research and Development in Information Retrieval, pp.318-329, 1992.","DOI":"10.1145\/133160.133214"},{"key":"48_CR08","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1093\/comjnl\/20.4.364","volume":"20","author":"D. Defays","year":"1977","unstructured":"Defays, D. An efficient algorithm for the complete link method. The Computer Journal, 20:364-366, 1977.","journal-title":"The Computer Journal"},{"key":"48_CR09","doi-asserted-by":"crossref","unstructured":"Dhillon, I.S. Co-clustering documents and words using Bipartite Spectral Graph Partitioning. UT CS Technical Report TR2001-05 20, 2001, (http:\/\/www.cs.texas.edu\/users\/inderjit\/public_papers\/kdd_bipartite.pdf).","DOI":"10.1145\/502512.502550"},{"key":"48_CR10","unstructured":"Ding, Y. IR and AI: The role of ontology. Proc. 4th International Conference of Asian Digital Libraries, Bangalore, India, 2001."},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"El-Hamdouchi, A., Willett, P. Hierarchic document clustering using Ward\u2019s method. Proceedings of the Ninth International Conference on Research and Development in Information Retrieval. ACM, Washington, pp.149-156, 1986.","DOI":"10.1145\/253168.253200"},{"key":"48_CR12","doi-asserted-by":"crossref","unstructured":"El-Hamdouchi, A., Willett, P. Comparison of hierarchic agglomerative clustering methods for document retrieval. The Computer Journal 32, 1989.","DOI":"10.1093\/comjnl\/32.3.220"},{"key":"48_CR13","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-009-5897-5","volume-title":"Finite Mixture Distributions","author":"B. S. Everitt","year":"1981","unstructured":"Everitt, B. S., Hand, D. J. Finite Mixture Distributions. London: Chapman and Hall, 1981."},{"issue":"1","key":"48_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0306-4573(94)E0005-M","volume":"31","author":"H. P. Frei","year":"1995","unstructured":"Frei, H. P., Stieger, D. The Use of Semantic Links in Hypertext Information Retrieval. Information Processing and Management, 31(1):1-13, 1995.","journal-title":"Information Processing and Management"},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Han, E.H., Boley, D., Gini, M., Gross, R., Hastings, K., Karypis, G., Kumar, V., Mobasher, B., Moore, J. WebACE: a web agent for document categorization and exploration. Technical Report TR-97-049, Department of Computer Science, University of Minnesota, Minneapolis, 1997, (http:\/\/www.users.cs.umn.edu\/karypis\/publications\/ir.html).","DOI":"10.1145\/280765.280872"},{"key":"48_CR16","doi-asserted-by":"crossref","unstructured":"Jain, A.K., Murty, M.N., Flyn, P.J. Data Clustering: A Review. ACM Computing Surveys, Vol. 31, No. 2, 1999.","DOI":"10.1145\/331499.331504"},{"issue":"8","key":"48_CR17","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1109\/2.781637","volume":"32","author":"G. Karypis","year":"1999","unstructured":"Karypis, G., Han, E.H, Kumar, V. CHAMELEON: A Hierarchical Clustering Algorithm Using Dynamic Modelling. IEEE Computer, 32(8):68- 75, 1999.","journal-title":"IEEE Computer"},{"key":"48_CR18","doi-asserted-by":"crossref","unstructured":"Karypis, G., Kumar, V. A fast and highly quality multilevel scheme for partitioning irregular graphs. SIAM Journal on Scientific Computing, 20(1), 1999.","DOI":"10.1137\/S1064827595287997"},{"key":"48_CR19","unstructured":"Kleinberg, J. Authoritative sources in a hyperlinked environment. Proc. of the 9th ACMSIAM Symposium on Discrete Algorithms, 1997."},{"key":"48_CR20","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-97610-0","volume-title":"Self-organizing maps","author":"T. Kohonen","year":"1995","unstructured":"Kohonen, T. Self-organizing maps. Springer-Verlag, Berlin, 1995."},{"key":"48_CR21","doi-asserted-by":"crossref","unstructured":"Kumar, S.R., Raghavan, P., Rajagopalan, S., Tomkins, A. Trawling the Web for Emerging Cyber-Communities. Proc. 8th WWW Conference, 1999.","DOI":"10.1016\/S1389-1286(99)00040-7"},{"key":"48_CR22","unstructured":"Larson, R.R. Bibliometrics of the World Wide Web: An Exploratory Analysis of the Intellectual Structure of Cyberspace. Proc. 1996 American Society for Information Science Annual Meeting, 1996."},{"key":"48_CR23","unstructured":"Looney, C. A Fuzzy Clustering and Fuzzy Merging Algorithm. Technical Report, CS-UNR-101-1999, 1999."},{"key":"48_CR24","unstructured":"Merkl, D. Text Data Mining. Dale, R., Moisl, H., Somers, H. (eds.), A handbook of natural language processing: techniques and applications for the processing of language as text, Marcel Dekker, New York"},{"key":"48_CR25","doi-asserted-by":"crossref","unstructured":"Modha, D., Spangler, W.S. Clustering hypertext with applications to web searching. Proc. ACM Conference on Hypertext and Hypermedia, 2000.","DOI":"10.1145\/336296.336351"},{"key":"48_CR26","doi-asserted-by":"crossref","unstructured":"Murtagh, F. A survey of recent advances in hierarchical clustering algorithms. The Computer Journal, 26:354-359","DOI":"10.1093\/comjnl\/26.4.354"},{"key":"48_CR27","unstructured":"Page, L., Brin, S., Motwani, R., Winograd, T. The PageRank citation ranking: Bringing order to the Web. Technical report, Stanford, 1998, (http:\/\/www.stanford.edu\/backrub\/pageranksub.ps)"},{"key":"48_CR28","doi-asserted-by":"crossref","unstructured":"Pirolli, P., Pitkow, J., Rao, R. Silk from a sow\u2019s ear: Extracting usable structures from the Web Proc. ACM SIGCHI Conference on Human Factors in Computing, 1996.","DOI":"10.1145\/238386.238450"},{"key":"48_CR29","unstructured":"Rasmussen, E. Clustering Algorithms. Information Retrieval,W.B. Frakes&R. Baeza-Yates, Prentice Hall PTR, New Jersey, 1992."},{"key":"48_CR30","first-page":"613","volume":"18","author":"G. Salton","year":"1975","unstructured":"Salton, G., Wang, A., Yang, C. A vector space model for information retrieval. Journal of the American Society for Information Science, 18:613\u2013620, 1975.","journal-title":"Journal of the American Society for Information Science"},{"key":"48_CR31","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1093\/comjnl\/16.1.30","volume":"16","author":"R. Sibson","year":"1973","unstructured":"Sibson, R. SLINK: an optimally efficient algorithm for the single link cluster method. The Computer Journal 16:30-34, 1973","journal-title":"The Computer Journal"},{"key":"48_CR32","unstructured":"Steinbach, M., G. Karypis, G., Kumar, V. A Comparison of Document Clustering Techniques. KDD Workshop on Text Mining, 2000."},{"key":"48_CR33","unstructured":"Strehl, A., Joydeep, G., Mooney, R. Impact of Similarity Measures on Web-page Clustering. Proc. 17th National Conference on Artificial Intelligence: Workshop of Artificial Intelligence for Web Search, pp.30-31, 2000."},{"key":"48_CR34","unstructured":"Van Rijsbergen, C. J. Information Retrieval. Butterworths, 1979."},{"key":"48_CR35","unstructured":"Varlamis, I., Vazirgiannis, M., Halkidi, M., Nguyen, B. THESUS: Effective Thematic Selection And Organization Of Web Document Collections based on Link Semantics. To appear in the IEEE Transactions on Knowledge And Data Engineering Journal"},{"key":"48_CR36","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/0306-4573(86)90097-X","volume":"22","author":"E. M. Voorhees","year":"1986","unstructured":"Voorhees, E. M. Implementing agglomerative hierarchic clustering algorithms for use in document retrieval. Information Processing & Management, 22: 465-476, 1986.","journal-title":"Information Processing & Management"},{"key":"48_CR37","doi-asserted-by":"crossref","unstructured":"Weiss, R., Velez, B., Sheldon, M., Nemprempre, C., Szilagyi, P., Gifford, D.K. HyPursuit: A Hierarchical Network Search Engine that Exploits Content-Link Hypertext Clustering. Proc. Seventh ACM Conference on Hypertext, 1996.","DOI":"10.1145\/234828.234846"},{"key":"48_CR38","first-page":"119","volume":"24","author":"D.H. White","year":"1989","unstructured":"White, D.H., McCain, K.W. Bibliometrics. Annual Review of Information Science Technology, 24:119-165, 1989.","journal-title":"Annual Review of Information Science Technology"},{"issue":"5","key":"48_CR39","first-page":"577","volume":"24","author":"P. Willett","year":"1988","unstructured":"Willett, P. Recent Trends in Hierarchic document Clustering: a critical review. Information & Management, 24(5):577-597, 1988.","journal-title":"Information & Management"},{"key":"48_CR40","doi-asserted-by":"crossref","unstructured":"Wu, Z., Palmer, M. Verb Semantics and Lexical Selection. 32nd Annual Meetings of the Associations for Computational Linguistics, pp.133-138, 1994.","DOI":"10.3115\/981732.981751"},{"key":"48_CR41","doi-asserted-by":"crossref","unstructured":"Zamir, O., Etzioni, O. Web document clustering: a feasibility demonstration. Proc. of SIGIR \u201998, Melbourne, Appendix-Questionnaire, pp.46-54, 1998.","DOI":"10.1145\/290941.290956"},{"key":"48_CR42","unstructured":"Zhao, Y., Karypis, G. Criterion Functions for Document Clustering: Experiments and Analysis. Technical Report 01-40. University of Minnesota, Computer Science Department. Minneapolis, MN, 2001 (http:\/\/wwwuserscs.umn.edu\/karypis\/publications\/ir.html.)"},{"key":"48_CR43","first-page":"515","volume":"16","author":"Y. Zhao","year":"2002","unstructured":"Zhao, Y., Karypis, G. Evaluation of Hierarchical Clustering Algorithms for Document Datasets. ACM Press, 16:515-524, 2002.","journal-title":"ACM Press"}],"container-title":["Data Mining and Knowledge Discovery Handbook"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-0-387-09823-4_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T23:41:43Z","timestamp":1675726903000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-0-387-09823-4_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9780387098227","9780387098234"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-0-387-09823-4_48","relation":{},"subject":[],"published":{"date-parts":[[2009]]},"assertion":[{"value":"7 July 2010","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}