{"id":"https://openalex.org/W304239299","doi":null,"title":"Ontology-based Text Document Clustering.","display_name":"Ontology-based Text Document Clustering.","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W304239299","mag":"304239299"},"language":"de","primary_location":{"id":"mag:304239299","doi":null,"is_oa":false,"landing_page_url":"https://www.kde.cs.uni-kassel.de/hotho/pub/Ontology_based_Text_Document_Clustering_2002.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S1001063841","display_name":"K\u00fcnstliche Intelligenz","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"K\u00fcnstliche Intelligenz","raw_type":null},"volume":null,"type":"book-chapter","is_traditional":true,"indexed_in":[],"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/A5062807811","display_name":"Steffen Staab","orcid":"https://orcid.org/0000-0002-0780-4154","observed_orcids":["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":"Steffen Staab","raw_affiliation_strings":["Karlsruhe Institute of technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054225034","display_name":"Andreas Hotho A","orcid":"https://orcid.org/0000-0002-0483-5772","observed_orcids":["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":"Andreas Hotho","raw_affiliation_strings":["Karlsruhe Institute of technology"],"raw_orcid":"https://orcid.org/0000-0002-0483-5772","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":4.44,"has_fulltext":false,"cited_by_count":155,"citation_normalized_percentile":{"value":0.94461142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"16","issue":null,"first_page":"451","last_page":"452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.8051999807357788,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.8051999807357788,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.1096000000834465,"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/T10028","display_name":"Topic Modeling","score":0.03060000017285347,"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/document-clustering","display_name":"document clustering","score":0.8849999904632568},{"id":"https://openalex.org/keywords/prior-knowledge","display_name":"prior knowledge","score":0.7889999747276306},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.9900000095367432},{"id":"https://openalex.org/keywords/feature-aggregation","display_name":"feature aggregation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"K-means clustering","score":0.6269999742507935},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.869157075881958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7104154825210571},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5665930509567261},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.545168399810791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5344955325126648},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5288934111595154},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5056469440460205},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5052614808082581},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.47962769865989685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45977601408958435},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4416017532348633},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4389042854309082},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.438772976398468},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:304239299","doi":null,"is_oa":false,"landing_page_url":"https://www.kde.cs.uni-kassel.de/hotho/pub/Ontology_based_Text_Document_Clustering_2002.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S1001063841","display_name":"K\u00fcnstliche Intelligenz","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"K\u00fcnstliche Intelligenz","raw_type":null},{"id":"mag:3217351091","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/iis/iis2003.html#StaabH03","pdf_url":null,"source":{"id":"https://openalex.org/S4210224544","display_name":"Intelligent information systems","issn_l":"1793-4990","issn":["1793-4990"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Intelligent information systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W46985669","https://openalex.org/W147860157","https://openalex.org/W1529320607","https://openalex.org/W1595303882","https://openalex.org/W1672197616","https://openalex.org/W1755193636","https://openalex.org/W1977496278","https://openalex.org/W2040058125","https://openalex.org/W2081580037","https://openalex.org/W2116184909","https://openalex.org/W2119689447","https://openalex.org/W2132626343","https://openalex.org/W2147152072","https://openalex.org/W2155033358","https://openalex.org/W2999729612"],"related_works":["https://openalex.org/W1736751365","https://openalex.org/W2121114441","https://openalex.org/W2133517430","https://openalex.org/W1581191794","https://openalex.org/W2373681485","https://openalex.org/W2372169033","https://openalex.org/W2746373291","https://openalex.org/W2545209521","https://openalex.org/W2145020055","https://openalex.org/W1569835270"],"abstract_inverted_index":{"Text":[0],"clustering":[1,4,25,69,108],"typically":[2,29],"involves":[3],"in":[5,65,125],"a":[6,23,36,56,95,133],"high":[7],"dimensional":[8],"space,":[9],"which":[10],"appears":[11],"difficult":[12],"with":[13,35,132],"regard":[14],"to":[15,32,67],"virtually":[16],"all":[17],"practical":[18],"settings.":[19],"In":[20,51],"addition,":[21],"given":[22],"particular":[24],"result":[26],"it":[27],"is":[28],"very":[30],"hard":[31],"come":[33],"up":[34],"good":[37],"explanation":[38],"of":[39,97,123],"why":[40],"the":[41,47,120,126],"text":[42,99],"clusters":[43],"have":[44],"been":[45],"constructed":[46],"way":[48],"they":[49],"are.":[50],"this":[52],"paper,":[53],"we":[54,93,105],"propose":[55],"new":[57],"approach":[58],"for":[59,73,86],"applying":[60,82],"background":[61],"knowledge":[62],"during":[63],"preprocessing":[64,136],"order":[66],"improve":[68],"results":[70,109,113,129],"and":[71,89,117],"allow":[72],"selection":[74,88,122],"between":[75],"results.":[76],"We":[77],"preprocess":[78],"our":[79],"input":[80],"data":[81],"an":[83],"ontology-based":[84],"heuristics":[85],"feature":[87,90],"aggregation.":[91],"Thus,":[92],"construct":[94],"number":[96],"alternative":[98],"representations.":[100],"Based":[101],"on":[102],"these":[103],"representations,":[104],"compute":[106],"multiple":[107],"using":[110],"KMeans.":[111],"The":[112],"may":[114],"be":[115],"distinguished":[116],"explained":[118],"by":[119],"corresponding":[121],"concepts":[124],"ontology.":[127],"Our":[128],"compare":[130],"favourably":[131],"sophisticated":[134],"baseline":[135],"strategy.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":16}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}