{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T07:59:43Z","timestamp":1770537583417,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":34,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540233053","type":"print"},{"value":"9783540301929","type":"electronic"}],"license":[{"start":{"date-parts":[[2004,1,1]],"date-time":"2004-01-01T00:00:00Z","timestamp":1072915200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-30192-9_59","type":"book-chapter","created":{"date-parts":[[2010,3,2]],"date-time":"2010-03-02T18:02:43Z","timestamp":1267552963000},"page":"597-606","source":"Crossref","is-referenced-by-count":27,"title":["An Overview of Web Data Clustering Practices"],"prefix":"10.1007","author":[{"given":"Athena","family":"Vakali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaroslav","family":"Pokorn\u00fd","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theodore","family":"Dalamagas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"59_CR1","volume-title":"Data on the Web","author":"S. Abiteboul","year":"2000","unstructured":"Abiteboul, S., Buneman, P., Suciu, D.: Data on the Web. Morgan Kaufmann, San Francisco (2000)"},{"key":"59_CR2","volume-title":"Modeling the Internet and the Web","author":"P. Baldi","year":"2003","unstructured":"Baldi, P., Frasconi, P., Smyth, P.: Modeling the Internet and the Web. Wiley, Chichester (2003)"},{"key":"59_CR3","unstructured":"Banerjee, A., Ghosh, J.: Clickstream clustering using weighted longest common Subsequences. In: Proceedings of Workshop on Web Mining, SIAM Conference on Data Mining, Chicago, USA, pp. 33\u201340 (April 2001)"},{"issue":"4","key":"59_CR4","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1023\/A:1024992613384","volume":"7","author":"I.V. Cadez","year":"2003","unstructured":"Cadez, I.V., Heckerman, D., Meek, C., Smyth, P., White, S.: Model-based clustering and visualization of navigation patterns on a Web site. Data Mining and Knowledge Discovery\u00a07(4), 399\u2013424 (2003)","journal-title":"Data Mining and Knowledge Discovery"},{"key":"59_CR5","volume-title":"Mining the Web","author":"S. Chakrabarti","year":"2003","unstructured":"Chakrabarti, S.: Mining the Web. Morgan Kaufmann, San Francisco (2003)"},{"key":"59_CR6","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1023\/A:1024606901978","volume":"6","author":"Z. Chen","year":"2003","unstructured":"Chen, Z., Wai-Chee Fu, A., Chi-Hung Tong, F.: Optimal algorithms for finding user access sessions from very large Web logs. World Wide Web: Internet and Information Systems\u00a06, 259\u2013279 (2003)","journal-title":"World Wide Web: Internet and Information Systems"},{"key":"59_CR7","unstructured":"Cobena, G., Abdessalem, T., Hinnach, Y.: A comparative study for XML change detection. Technical Report, INRIA, France (2000)"},{"key":"59_CR8","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/BF03325089","volume":"1","author":"R. Cooley","year":"1999","unstructured":"Cooley, R., Mobasher, B., Srivastava, J.: Data preparation for mining World Wide Web browsing patterns. Knowledge Information Systems\u00a01, 5\u201332 (1999)","journal-title":"Knowledge Information Systems"},{"key":"59_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/3-540-36618-0_6","volume-title":"Advances in Information Retrieval","author":"H. Cui","year":"2003","unstructured":"Cui, H., Wen, J.-R.: Hierarchical indexing and flexible element retrieval for structured document. In: Sebastiani, F. (ed.) ECIR 2003. LNCS, vol.\u00a02633, pp. 73\u201387. Springer, Heidelberg (2003)"},{"key":"59_CR10","first-page":"1","volume":"39","author":"A.P. Dempster","year":"1997","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Statistics Society B\u00a039, 1\u201322 (1997)","journal-title":"Statistics Society B"},{"key":"59_CR11","doi-asserted-by":"crossref","unstructured":"Eiron, N., McCurley, K.S.: Untangling compound documents on the Web. In: Proceedings of ACM Hypertext, pp. 85\u201394 (2003)","DOI":"10.1145\/900069.900070"},{"key":"59_CR12","doi-asserted-by":"crossref","unstructured":"Flake, G.W., Lawrence, S., Lee Giles, C., Coetzee, F.: Self-organization and identification of Web Communities. IEEE Computer\u00a035(3) (2002)","DOI":"10.1109\/2.989932"},{"key":"59_CR13","unstructured":"Flesca, S., Manco, G., Masciari, E., Pontieri, L., Pugliese, A.: Detecting similarities between XML documents. In: Proceedings of WebDB Workshop (2002)"},{"key":"59_CR14","doi-asserted-by":"crossref","unstructured":"Fraley, C., Raftery, A.: How many clusters? Which clustering method? Answers via model-based cluster analysis. Computer Journal\u00a041 (1998)","DOI":"10.1093\/comjnl\/41.8.578"},{"key":"59_CR15","doi-asserted-by":"crossref","unstructured":"Fuhr, N., Gro\u03b2johann, K.: XIRQL: a query language for information retrieval in XML documents. In: Proceedings of ACM SIGIR (2001)","DOI":"10.1145\/383952.383985"},{"key":"59_CR16","unstructured":"Fu, Y., Sandhu, K., Shih, M.-Y.: Clustering of Web users based on access patterns. In: Proceedings of WEBKDD (1999)"},{"key":"59_CR17","unstructured":"Grabs, T., Org Schek, H.-J.: Generating vector spaces on-the-fly for flexible XML retrieval. In: Proceedings of XML and IR Workshop (2002)"},{"issue":"1","key":"59_CR18","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1023\/B:WWWJ.0000015865.63749.b2","volume":"7","author":"G. Greco","year":"2004","unstructured":"Greco, G., Greco, S., Zumpano, E.: Web communities: models and algorithms. World Wide Web\u00a07(1), 58\u201382 (2004)","journal-title":"World Wide Web"},{"key":"59_CR19","doi-asserted-by":"crossref","unstructured":"Guha, S., Rastogi, R., Shim, K.: ROCK: A robust clustering algorithm for categorical attributes. ACM SIGMOD Record\u00a025(5) (2000)","DOI":"10.1016\/S0306-4379(00)00022-3"},{"key":"59_CR20","unstructured":"Hay, B., Vanhoof, K., Wetsr, G.: Clustering navigation patterns on a Website using a sequence alignment method. In: Proceedings of 17th International Joint Conference on Artificial Intelligence, Seattle, Washington, USA (August 2001)"},{"key":"59_CR21","unstructured":"Kleinberg, J.M.: Authoritative sources in a hyper-linked environment. In: Proceedings of the 9th ACM-SIAM Symposium on Discrete Algorithm (1998)"},{"key":"59_CR22","unstructured":"Mass, Y., Mandelbrod, M., Amitay, E., Maarek, Y., Soffer, A.: Juru XML - an XML retrieval system at INEX 2002. In: Proceedings of INEX, Dagstuhl, Germany (December 2002)"},{"key":"59_CR23","doi-asserted-by":"crossref","unstructured":"Myaeng, S.H., Jang, D.-H.: A flexible model for retrieval of SGML documents. In: Proceedings of ACM SIGIR (1998)","DOI":"10.1145\/290941.290980"},{"key":"59_CR24","unstructured":"Nierman, A., Jagadish, H.V.: Evaluating structural similarity in XML documents. In: Proceedings of the WebDB Workshop, Madison, Wisconsin, USA (June 2002)"},{"key":"59_CR25","doi-asserted-by":"crossref","unstructured":"Kothari, R., Mittal, P.A., Jain, V., Mohania, M.K.: On using page cooccurrences for computing clickstream similarity. In: Proceedings of the 3rd SIAM International Conference on Data Mining, San Francisco, USA (May 2003)","DOI":"10.1137\/1.9781611972733.14"},{"key":"59_CR26","volume-title":"Time warps, string edits and macromolecules, the theory and practice of sequence comparison","author":"D. Sankoff","year":"1999","unstructured":"Sankoff, D., Kruskal, J.: Time warps, string edits and macromolecules, the theory and practice of sequence comparison. CSLI Publications, Stanford (1999)"},{"key":"59_CR27","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/S1389-1286(00)00044-X","volume":"33","author":"R.R. Sarukkai","year":"2000","unstructured":"Sarukkai, R.R.: Link prediction and path analysis using Markov chains. Computer Networks\u00a033, 377\u2013386 (2000)","journal-title":"Computer Networks"},{"key":"59_CR28","unstructured":"Su, Z., Yang, Q., Zhang, H.H., Xu, X., Hu, Y.: Correlation-based document clustering using Web logs. In: Proceedings of the 34th Annual Hawaii International Conference on System Sciences (HICSS-34), Maui, Hawaii (January 2001)"},{"key":"59_CR29","unstructured":"Tajima, K., Hatano, K., Matsukura, T., Sano, R., Tanaka, K.: Discovery and retrieval of logical information units in Web. In: Proceedings of the Workshop on Organizing Web Space (WOWS 1999), Berkeley, USA, pp. 13\u201323 (August 1999)"},{"key":"59_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/3-540-45876-X_31","volume-title":"Advances in Database Technology - EDBT 2002","author":"A. Theobald","year":"2002","unstructured":"Theobald, A., Weikum, G.: The Index-Based XXL Search engine for querying XML data with relevance ranking. In: Jensen, C.S., Jeffery, K., Pokorn\u00fd, J., \u0160altenis, S., Bertino, E., B\u00f6hm, K., Jarke, M. (eds.) EDBT 2002. LNCS, vol.\u00a02287, p. 477. Springer, Heidelberg (2002)"},{"key":"59_CR31","volume-title":"Modern information retrieval","author":"R. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates, R., Ribiero-Neto, B.: Modern information retrieval. Addison-Wesley, Reading (1999)"},{"key":"59_CR32","doi-asserted-by":"crossref","unstructured":"Baeza-Yates, R., Navarro, G.: Integrating contents and structure in text retrieval. ACM SIGMOD Record\u00a025(1) (1996)","DOI":"10.1145\/381854.381890"},{"key":"59_CR33","doi-asserted-by":"crossref","unstructured":"Yoon, J., Raghavan, V., Chakilam, V., Kerschberg, L.: BitCube: A three-dimensional bitmap indexing for XML documents. Journal of Intelligent Information Systems\u00a017 (2001)","DOI":"10.1023\/A:1012861931139"},{"key":"59_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, T., Ramakrishnan, R., Livny, M.: BIRCH: An efficient data clustering method for very large databases. In: Proceedings of the International Conference Management of Data (ACM-SIGMOD), Montreal, Canada, pp. 103\u2013114 (June 1996)","DOI":"10.1145\/235968.233324"}],"container-title":["Lecture Notes in Computer Science","Current Trends in Database Technology - EDBT 2004 Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-30192-9_59","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T17:29:17Z","timestamp":1558286957000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-30192-9_59"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540233053","9783540301929"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-30192-9_59","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2004]]}}}