{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T14:30:56Z","timestamp":1761489056418},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,1,4]],"date-time":"2013-01-04T00:00:00Z","timestamp":1357257600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2015,3]]},"DOI":"10.1007\/s10462-012-9379-2","type":"journal-article","created":{"date-parts":[[2013,1,3]],"date-time":"2013-01-03T08:17:32Z","timestamp":1357201052000},"page":"417-436","source":"Crossref","is-referenced-by-count":6,"title":["XML document clustering: techniques and challenges"],"prefix":"10.1007","volume":"43","author":[{"given":"Elaheh","family":"Asghari","sequence":"first","affiliation":[]},{"given":"MohammadReza","family":"KeyvanPour","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,1,4]]},"reference":[{"key":"9379_CR1","unstructured":"Alshahat A, Algergawy A (2010) Management of xml data by means of schema matching. Publisher Dr, Hut. ISBN 3868533834, 9783868533835"},{"key":"9379_CR2","doi-asserted-by":"crossref","unstructured":"Antonellis P, Makris C, Tsirakis N (2008) XEdge: clustering homogeneous and heterogeneous XML documents using edge summaries. In: Proceedings of the 2008 ACM symposium on applied computing (SAC \u201908). ACM, New York, NY, USA, pp 1081\u20131088","DOI":"10.1145\/1363686.1363940"},{"key":"9379_CR3","unstructured":"Bray T, Paoli J (2000) Extensible markup language (XML) 1.0, 2nd edn. Sperberg-McQueen CM University of Illinois at Chicago and text encoding initiative. Sun Microsystems Inc, Eve Maler"},{"key":"9379_CR4","doi-asserted-by":"crossref","unstructured":"Dalamagas T, Cheng T, Winkel KJ, Sellis T (2006) A methodology for clustering XML documents by structure. Inf Syst 31(3):187\u2013228","DOI":"10.1016\/j.is.2004.11.009"},{"key":"9379_CR5","unstructured":"Doucet A, Lehtonen M (2006) Unsupervised classification of text-centric XML document collections. In: Comparative evaluation of XML information retrieval systems, 5th international workshop of the initiative for the evaluation of XML retrieval, INEX 2006, Dagstuhl Castle, Germany, December 17\u201320, 2006, Revised and selected papers. Volume 4518 of Lecture Notes in Computer Science. Springer, pp 497\u2013509"},{"key":"9379_CR6","unstructured":"Doucet A, Myka HA (2002) Naive clustering of a large XML document collection. In: Proceedings of the INEX annual ERCIM, workshop, pp 81\u201388"},{"key":"9379_CR7","unstructured":"Flesca S, Manco G, Masciari E, Pontieri L, Pugliese A (2002) Detecting structural similarities between XML documents. In: Proceedings of the international workshop on the web and databases (WebDB)"},{"issue":"2","key":"9379_CR8","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1109\/TKDE.2005.27","volume":"17","author":"S Flesca","year":"2005","unstructured":"Flesca S, Manco G, Masciari E, Pontieri L (2005) Fast detection of XML structural similarity. IEEE Trans Knowl Data Eng 17(2):160\u2013175","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"9379_CR9","unstructured":"Kozielski M (2007) Application of different clustering algorithms to multilevel clustering of XML documents, vol 16. Institute of Informatics, Silesian University of Technology, Akademicka Gliwice, pp 44\u2013100"},{"issue":"1","key":"9379_CR10","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/TKDE.2004.1264824","volume":"16","author":"W Lian","year":"2004","unstructured":"Lian W, Cheung DW, Mamoulis N, Yiu SM (2004) An efficient and scalable algorithm for clustering XML documents by structure. IEEE Trans Knowl Data Eng 16(1):82\u201396","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"9379_CR11","doi-asserted-by":"crossref","unstructured":"Nayak R (2006) Investigating semantic measures in XML clustering. In: Proceedings of the (2006) IEEE\/WIC\/ACM international conference on web intelligence (WI \u201906). IEEE Computer Society, Washington, DC, USA, pp 1042\u20131045","DOI":"10.1109\/WI.2006.106"},{"key":"9379_CR12","unstructured":"Nayak R, De Vries CM, Kutty S, Geva Sh, Denoyer L, Gallinari P (2009) Overview of the INEX 2009 XML mining track : clustering and classification of XML documents. In: Focused retrieval and evaluation: proceedings of 8th international workshop of the initiative for the evaluation of XML retrieval, INEX (2009). Springer, Brisbane, Queensland, pp 366\u2013378"},{"key":"9379_CR13","unstructured":"Nayak R, Xu S (2006) XCLS: a fast and effective clustering algorithm for heterogenous XML documents. In: Ng WK, Kitsuregawa M, Chang K (eds) Advances in knowledge discovery and data mining: proceedings of the 10th Pacific-Asia conference (LNCS 3918) 9\u201312 April, 2006, Singapore"},{"key":"9379_CR14","unstructured":"Nierman A, Jagadish HV (2002) Evaluating structural similarity in XML documents. In: Proceedings ACM SIGMOD WebDB (international workshop on the web and databases), workshop, pp 61\u201366"},{"key":"9379_CR15","unstructured":"Ruso LR (2012) XML data mining, part 3: clustering XML documents for improved data mining. DW and BI consultant, computershare technology services Australia, La Trobe University Australia, Development Team Lead"},{"key":"9379_CR16","doi-asserted-by":"crossref","unstructured":"Tagarelli A, Greco S (2006) Toward semantic XML clustering. In: Proceedings of the sixth SIAM international conference on data mining, University of Calabria","DOI":"10.1137\/1.9781611972764.17"},{"issue":"1","key":"9379_CR17","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/1658377.1658380","volume":"28","author":"A Tagarelli","year":"2010","unstructured":"Tagarelli A, Greco S (2010) Semantic clustering of XML documents. ACM Trans Inf Syst 28(1):3","journal-title":"ACM Trans Inf Syst"},{"key":"9379_CR18","doi-asserted-by":"crossref","unstructured":"Yang J, Cheung W K, Chen X (2005) Learning the Kernel matrix for XML document clustering. In: IEEE international conference on e-technology, e-commerce and e-service, pp 353\u2013358","DOI":"10.1109\/EEE.2005.87"},{"key":"9379_CR19","doi-asserted-by":"crossref","unstructured":"Yang R, Kalnis P, Tung A (2005) Similarity evaluation on tree-structured data. In: Proceedings of the ACM international conference on management of data, pp 754\u2013765","DOI":"10.1145\/1066157.1066243"},{"key":"9379_CR20","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1023\/A:1012861931139","volume":"17","author":"J Yoon","year":"2001","unstructured":"Yoon J, Raghavan V, Chakilam V, Kerschberg V (2001) BitCube: a three-dimensional bitmap indexing for XML documents. J Intell Inf Syst 17:241\u2013254","journal-title":"J Intell Inf Syst"},{"issue":"6","key":"9379_CR21","doi-asserted-by":"crossref","first-page":"1245","DOI":"10.1137\/0218082","volume":"18","author":"K Zhang","year":"1989","unstructured":"Zhang K, Shasha D (1989) Simple fast algorithms for the editing distance between trees and related problems. SIAM J Comput 18(6):1245\u20131262","journal-title":"SIAM J Comput"},{"key":"9379_CR22","doi-asserted-by":"crossref","unstructured":"Zhao B, Zhang Y, Zhang H (2008) A robust clustering method for XML documents. In: International conference on information management, innovation management and industrial engineering","DOI":"10.1109\/ICIII.2008.181"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-012-9379-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-012-9379-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-012-9379-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,7]],"date-time":"2019-07-07T21:26:34Z","timestamp":1562534794000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-012-9379-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,1,4]]},"references-count":22,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2015,3]]}},"alternative-id":["9379"],"URL":"https:\/\/doi.org\/10.1007\/s10462-012-9379-2","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,1,4]]}}}