{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T13:46:22Z","timestamp":1774014382631,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2011,1,29]],"date-time":"2011-01-29T00:00:00Z","timestamp":1296259200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2011,8]]},"DOI":"10.1007\/s10115-010-0370-4","type":"journal-article","created":{"date-parts":[[2011,1,28]],"date-time":"2011-01-28T17:58:29Z","timestamp":1296237509000},"page":"395-421","source":"Crossref","is-referenced-by-count":70,"title":["On ontology-driven document clustering using core semantic features"],"prefix":"10.1007","volume":"28","author":[{"given":"Samah","family":"Fodeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bill","family":"Punch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pang-Ning","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,1,29]]},"reference":[{"key":"370_CR1","doi-asserted-by":"crossref","unstructured":"Andrzejewski D, Zhu X, Craven M (2009) Incorporating domain knowledge into topic modeling via dirichlet forest priors. ICML 25\u201332","DOI":"10.1145\/1553374.1553378"},{"key":"370_CR2","unstructured":"Al Sumait L, Domeniconi C (2007) Local semantic kernels for text document clustering. In: SIAM international conference on data mining workshop on text mining"},{"key":"370_CR3","doi-asserted-by":"crossref","unstructured":"Banerjee S, Ramanathan K, Gupta A (2007) Clustering short texts using Wikipedia. SIGIR 787\u2013788","DOI":"10.1145\/1277741.1277909"},{"key":"370_CR4","unstructured":"Basu S, Banerjee A, Mooney RJ (2002) Semi-supervised clustering by seeding. ICML 19\u201326"},{"key":"370_CR5","unstructured":"Bodner RC, Song F(1996) Knowledge-based approaches to query expansion in information retrieval. Adv Artif Intell 146\u2013158"},{"key":"370_CR6","unstructured":"CLUTO Family of Clustering Software Tools: http:\/\/glaros.dtc.umn.edu\/gkhome\/cluto\/cluto\/overview"},{"key":"370_CR7","doi-asserted-by":"crossref","unstructured":"Craven M, DiPasquo D, Freitag D, McCallum A, Mitchell TM et\u00a0al (2000) Learning to construct knowledge bases from the World Wide Web. Artif Intell 118:69\u2013113","DOI":"10.1016\/S0004-3702(00)00004-7"},{"key":"370_CR8","doi-asserted-by":"crossref","unstructured":"Chemudugunta C, Smyth P, Steyvers M (2008) Combining concept hierarchies and statistical topic models. CIKM 1469\u20131470","DOI":"10.1145\/1458082.1458337"},{"key":"370_CR9","doi-asserted-by":"crossref","unstructured":"Dhillon I, Mallela S, Modha D (2003) Information-theoretic co-clustering. KDD 89\u201398","DOI":"10.1145\/956750.956764"},{"key":"370_CR10","unstructured":"Farahat AK, Kamel MS (2010) Enhancing document clustering using hybrid models for semantic similarity. In: SIAM international conference on data mining workshop on text mining"},{"key":"370_CR11","doi-asserted-by":"crossref","unstructured":"Fodeh SJ, Punch W, Tan PN (2009) Combining statistics and semantics via ensemble model for document clustering. SAC 1446\u20131450","DOI":"10.1145\/1529282.1529605"},{"key":"370_CR12","first-page":"1301","volume":"21","author":"E Gabrilovich","year":"2006","unstructured":"Gabrilovich E, Markovitch S (2006) Overcoming the brittleness bottleneck using Wikipedia: enhancing text categorization with encyclopedic knowledge. NCAI 21: 1301\u20131306","journal-title":"NCAI"},{"key":"370_CR13","unstructured":"Gabrilovich E, Markovitch S (2007) Computing semantic relatedness using Wikipedia-based explicit semantic analysis. IJCAI 1606\u20131611"},{"key":"370_CR14","unstructured":"Hotho A, Staab S, Stumme G (2003) WordNet improves text document clustering. In: SIGIR 2003 semantic web workshop. 541\u2013544"},{"key":"370_CR15","doi-asserted-by":"crossref","unstructured":"Hu J, Fang L, Cao Y (2008) Enhancing text clustering by leveraging Wikipedia semantics. SIGIR 179\u2013186","DOI":"10.1145\/1390334.1390367"},{"key":"370_CR16","doi-asserted-by":"crossref","unstructured":"Hu X, Sun N, Zhang C, Chua TS (2009) Exploiting internal and external semantics for the clustering of short texts using world knowledge. CIKM 919\u2013928","DOI":"10.1145\/1645953.1646071"},{"key":"370_CR17","unstructured":"Ifrim G, Theobald M, Weikum G (2005) Learning word-to-concept mappings for automated text classification. In: Workshop on learning in web search (LWS 2005). 18\u201325"},{"key":"370_CR18","unstructured":"Jiang JJ, Conrath DW (1997) Semantic similarity based on corpus statistics and lexical taxonomy. International Conference Research on Computational Linguistics (ROCLING X)"},{"key":"370_CR19","unstructured":"Jing L, Zhou L, Ng MK, Huang JZ (2006) Ontology-based distance measure for text clustering. In: SIAM SDM workshop on text mining"},{"key":"370_CR20","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10115-008-0135-5","volume":"17","author":"V Kandylas","year":"2009","unstructured":"Kandylas V, Upham SP, Ungar LH (2009) Finding cohesive clusters for analyzing knowledge communities. Knowl Inf Syst 17: 335\u2013354","journal-title":"Knowl Inf Syst"},{"key":"370_CR21","doi-asserted-by":"crossref","unstructured":"Lang K (1995) NewsWeeder: learning to filter netnews. ICML 331\u2013339","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"370_CR22","doi-asserted-by":"crossref","unstructured":"Larsen B, Aone C (1999) Fast and effective text mining using linear-time document clustering. KDD 16\u201322","DOI":"10.1145\/312129.312186"},{"key":"370_CR23","unstructured":"Lewis D (1997) Reuters-21578 text categorization test collection. AT&T Labs Research"},{"key":"370_CR24","first-page":"296","volume":"1","author":"D Lin","year":"1998","unstructured":"Lin D (1998) An information-theoretic definition of similarity. ICML 1: 296\u2013304","journal-title":"ICML"},{"key":"370_CR25","doi-asserted-by":"crossref","unstructured":"Mandala R, Tokunaga T, Tanaka H (1999) Complementing WordNet with Roget\u2019s and Corpus-based Thesauri for information retrieval. In: The 9th conference of the European chapter of the association for computational linguistics. 94\u2013101","DOI":"10.3115\/977035.977049"},{"key":"370_CR26","unstructured":"MeSH, National Library of Medicine Controlled Vocabulary: http:\/\/www.nlm.nih.gov\/mesh"},{"key":"370_CR27","unstructured":"Moravec P, Kolovrat M, Snasel V (2004) LSI vs. WordNet ontology in dimension reduction and information retrieval. DATESO 288\u2013294"},{"key":"370_CR28","unstructured":"Natural Language Toolkit: http:\/\/www.nltk.org"},{"key":"370_CR29","first-page":"563","volume":"10","author":"D Recupero","year":"2007","unstructured":"Recupero D (2007) A new unsupervised method for Document Clustering by using WordNet Lexical and Conceptual Relations. SIGIR 10: 563\u2013579","journal-title":"SIGIR"},{"key":"370_CR30","unstructured":"Rosso P, Ferretti E, Jimenez D et\u00a0al (2004) Text categorization and information retrieval using WordNet senses. In: 2nd Global WordNet international conference. 299\u2013304"},{"key":"370_CR31","doi-asserted-by":"crossref","unstructured":"Sedding J, Kazakov D (2004) WordNet-based text document clustering. In: 3rd workshop on Robust methods in analysis of natural language processing data. 104\u2013113","DOI":"10.3115\/1621445.1621458"},{"key":"370_CR32","first-page":"205","volume":"5","author":"G Siolas","year":"2004","unstructured":"Siolas G, d\u2019Alche Buc F (2004) Support vector machines based on a semantic kernel for text categorization. IJCNN\u201900 5: 205\u2013209","journal-title":"IJCNN\u201900"},{"key":"370_CR33","doi-asserted-by":"crossref","unstructured":"Slonim N, Tishby N (2000) Document clustering using word clusters via the information bottleneck method. SIGIR 208\u2013215","DOI":"10.1145\/345508.345578"},{"key":"370_CR34","unstructured":"Steinbach M, Karypis G, Kumar V (2000) A comparison of document clustering techniques. In: Proceedings of KDD workshop on text mining 34:35\u201336"},{"key":"370_CR35","volume-title":"Introduction to data mining","author":"PN Tan","year":"2005","unstructured":"Tan PN, Steinbach M, Kumar V (2005) Introduction to data mining. Addison-Wesley Longman Publishing Co, Boston"},{"key":"370_CR36","first-page":"49","volume":"1","author":"A Termier","year":"2001","unstructured":"Termier A, Rousset MC, Sebag M (2001) Combining statistics and semantics for word and document clustering. IJCAI 1: 49\u201354","journal-title":"IJCAI"},{"key":"370_CR37","unstructured":"The 20 Newsgroups data set: http:\/\/people.csail.mit.edu\/jrennie\/20Newsgroups\/"},{"key":"370_CR38","doi-asserted-by":"crossref","unstructured":"Vorhees E (1993) Using WordNet to disambiguate word senses for text retrieval. SIGIR 171\u2013180","DOI":"10.1145\/160688.160715"},{"key":"370_CR39","doi-asserted-by":"crossref","unstructured":"Wang P, Hu J, Zeng HJ et\u00a0al (2007) Improving text classification by using encyclopedia knowledge. ICDM 332\u2013341","DOI":"10.1109\/ICDM.2007.77"},{"key":"370_CR40","doi-asserted-by":"crossref","unstructured":"Wang P, Domeniconi C (2008) Building semantic kernels for text classification using Wikipedia. KDD 713\u2013721","DOI":"10.1145\/1401890.1401976"},{"key":"370_CR41","doi-asserted-by":"crossref","unstructured":"Wang Y, Hodges J (2006) Document clustering with semantic analysis. HICSS 3:54c\u201354c","DOI":"10.1109\/HICSS.2006.129"},{"key":"370_CR42","unstructured":"Wikipedia: http:\/\/wikipedia.edu"},{"key":"370_CR43","unstructured":"WordNet: http:\/\/wordnet.princeton.edu"},{"key":"370_CR44","unstructured":"Wu Z, Palmer M Verb (1994) Semantics and lexical selection. MACL 133\u2013138"},{"key":"370_CR45","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s10115-008-0158-y","volume":"19","author":"H Xiong","year":"2009","unstructured":"Xiong H, Steinbach M, Ruslim A et\u00a0al (2009) Characterizing pattern preserving clustering. Knowl Inf Syst 19: 133\u2013138","journal-title":"Knowl Inf Syst"},{"key":"370_CR46","doi-asserted-by":"crossref","unstructured":"Yoo I, Hu X, Song I (2006) Integration of semantic-based bipartite graph representation and mutual refinement strategy for biomedical literature clustering. KDD 791\u2013796","DOI":"10.1145\/1150402.1150505"},{"key":"370_CR47","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 (2005) Generative model-based document clustering: a comparative study. Knowl Inf Syst 8: 374\u2013384","journal-title":"Knowl Inf Syst"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-010-0370-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-010-0370-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-010-0370-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,2]],"date-time":"2025-03-02T06:59:23Z","timestamp":1740898763000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-010-0370-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,1,29]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2011,8]]}},"alternative-id":["370"],"URL":"https:\/\/doi.org\/10.1007\/s10115-010-0370-4","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,1,29]]}}}