{"id":"https://openalex.org/W2133517430","doi":"https://doi.org/10.1109/icdm.2003.1250972","title":"Ontologies improve text document clustering","display_name":"Ontologies improve text document clustering","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2133517430","doi":"https://doi.org/10.1109/icdm.2003.1250972","mag":"2133517430"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1250972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054225034","display_name":"Andreas Hotho","orcid":"https://orcid.org/0000-0002-0483-5772"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Hotho","raw_affiliation_strings":["Institute AIFB, University of Karlsruhe, Karlsruhe, Germany","Inst. fur Angewandte Inf. und Formale Beschreibungsverfahren, Karlsruhe Univ., Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute AIFB, University of Karlsruhe, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Inst. fur Angewandte Inf. und Formale Beschreibungsverfahren, Karlsruhe Univ., Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062807811","display_name":"Steffen Staab","orcid":"https://orcid.org/0000-0002-0780-4154"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S. Staab","raw_affiliation_strings":["Institute AIFB, University of Karlsruhe, Karlsruhe, Germany","Inst. fur Angewandte Inf. und Formale Beschreibungsverfahren, Karlsruhe Univ., Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute AIFB, University of Karlsruhe, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Inst. fur Angewandte Inf. und Formale Beschreibungsverfahren, Karlsruhe Univ., Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053751744","display_name":"Gerd Stumme","orcid":"https://orcid.org/0000-0002-0570-7908"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"G. Stumme","raw_affiliation_strings":["Institute AIFB, University of Karlsruhe, Karlsruhe, Germany","Inst. fur Angewandte Inf. und Formale Beschreibungsverfahren, Karlsruhe Univ., Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute AIFB, University of Karlsruhe, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Inst. fur Angewandte Inf. und Formale Beschreibungsverfahren, Karlsruhe Univ., Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":22.2053,"has_fulltext":false,"cited_by_count":353,"citation_normalized_percentile":{"value":0.99463295,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"541","last_page":"544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8558851480484009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8209174871444702},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7346896529197693},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6866384744644165},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.5442429184913635},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.44290733337402344},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4234168231487274},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3317342698574066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3014751076698303},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.1813550889492035}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8558851480484009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209174871444702},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7346896529197693},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6866384744644165},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.5442429184913635},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.44290733337402344},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4234168231487274},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3317342698574066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3014751076698303},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.1813550889492035},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdm.2003.1250972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.321","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aifb.uni-karlsruhe.de/WBS/sst/Research/Publications/icdem-hothoa_ontologies.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W21550605","https://openalex.org/W1651093245","https://openalex.org/W1731244441","https://openalex.org/W1966415964","https://openalex.org/W2081580037","https://openalex.org/W2132135775","https://openalex.org/W4285719527","https://openalex.org/W6600892349","https://openalex.org/W6632999740","https://openalex.org/W6637231022","https://openalex.org/W6637672553"],"related_works":["https://openalex.org/W2945382830","https://openalex.org/W4224807364","https://openalex.org/W2596632494","https://openalex.org/W2899601636","https://openalex.org/W4206655101","https://openalex.org/W2019737068","https://openalex.org/W3015674157","https://openalex.org/W3192757256","https://openalex.org/W2049508213","https://openalex.org/W2378900857"],"abstract_inverted_index":{"Text":[0],"document":[1],"clustering":[2,35,70,77],"plays":[3],"an":[4,93],"important":[5,45],"role":[6],"in":[7,117],"providing":[8],"intuitive":[9],"navigation":[10],"and":[11,87],"browsing":[12],"mechanisms":[13],"by":[14,104],"organizing":[15],"large":[16],"sets":[17],"of":[18,24,29,69,82,92,102],"documents":[19],"into":[20,66],"a":[21,89,109],"small":[22],"number":[23],"meaningful":[25],"clusters.":[26],"The":[27],"bag":[28],"words":[30],"representation":[31],"used":[32],"for":[33],"these":[34],"methods":[36],"is":[37],"often":[38],"unsatisfactory":[39],"as":[40,63],"it":[41],"ignores":[42],"relationships":[43],"between":[44],"terms":[46],"that":[47],"do":[48],"not":[49],"cooccur":[50],"literally.":[51],"In":[52,98],"order":[53],"to":[54,108],"deal":[55],"with":[56],"the":[57,67,99],"problem,":[58],"we":[59],"integrate":[60],"core":[61],"ontologies":[62],"background":[64,105,112],"knowledge":[65,106,113],"process":[68],"text":[71],"documents.":[72],"Our":[73],"experimental":[74],"evaluations":[75],"compare":[76],"techniques":[78],"based":[79],"on":[80,88],"pre-categorizations":[81],"texts":[83],"from":[84],"Reuters":[85],"newsfeeds":[86],"smaller":[90],"domain":[91],"eLearning":[94],"course":[95],"about":[96],"Java.":[97],"experiments,":[100],"improvements":[101],"results":[103],"compared":[107],"baseline":[110],"without":[111],"can":[114],"be":[115],"shown":[116],"many":[118],"interesting":[119],"combinations.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":26},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":27},{"year":2012,"cited_by_count":13}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}