{"id":"https://openalex.org/W2145429017","doi":"https://doi.org/10.1093/comjnl/bxr024","title":"Exploiting Wikipedia Knowledge for Conceptual Hierarchical Clustering of Documents","display_name":"Exploiting Wikipedia Knowledge for Conceptual Hierarchical Clustering of Documents","publication_year":2011,"publication_date":"2011-03-15","ids":{"openalex":"https://openalex.org/W2145429017","doi":"https://doi.org/10.1093/comjnl/bxr024","mag":"2145429017"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxr024","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxr024","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://doi.org/10.1093/comjnl/bxr024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010354377","display_name":"Gerasimos Spanakis","orcid":"https://orcid.org/0000-0002-0799-0241"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"G. Spanakis","raw_affiliation_strings":["Intelligent Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066222732","display_name":"Georgios Siolas","orcid":"https://orcid.org/0000-0002-4839-7831"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"G. Siolas","raw_affiliation_strings":["Intelligent Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108612969","display_name":"Andreas Stafylopatis","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"A. Stafylopatis","raw_affiliation_strings":["Intelligent Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens, 15780, Zografou, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010354377"],"corresponding_institution_ids":["https://openalex.org/I174458059"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":5.1765,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95534578,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"55","issue":"3","first_page":"299","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9976999759674072,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9976999759674072,"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":0.9855999946594238,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5642534494400024},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.4777897298336029},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4108927249908447},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3709723949432373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12019127607345581}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5642534494400024},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.4777897298336029},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4108927249908447},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3709723949432373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12019127607345581}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/comjnl/bxr024","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxr024","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/29761","is_oa":true,"landing_page_url":"http://doi.org/10.1093/comjnl/bxr024","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Journal","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/29761","is_oa":true,"landing_page_url":"http://doi.org/10.1093/comjnl/bxr024","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Journal","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"novel":[6],"method":[7,21],"for":[8,80,89],"conceptual":[9],"hierarchical":[10,67],"clustering":[11,64],"of":[12,31,72,108],"documents":[13],"using":[14,48,76],"knowledge":[15],"extracted":[16],"from":[17],"Wikipedia.":[18],"The":[19,63],"proposed":[20,97],"overcomes":[22],"the":[23,29,49,55,70,90,96,102,113,120],"classic":[24],"bag-of-words":[25],"models":[26],"disadvantages":[27],"through":[28],"exploitation":[30],"Wikipedia":[32,50,61,77],"textual":[33],"content":[34],"and":[35,40,68,87,110,116],"link":[36],"structure.":[37],"A":[38],"robust":[39],"compact":[41],"document":[42],"representation":[43],"is":[44,66],"built":[45],"in":[46,106],"real-time":[47],"application":[51],"programmer's":[52],"interface,":[53],"without":[54],"need":[56],"to":[57],"store":[58],"locally":[59],"any":[60],"information.":[62],"process":[65],"extends":[69],"idea":[71],"frequent":[73],"items":[74],"by":[75],"article":[78],"titles":[79],"selecting":[81],"cluster":[82],"labels":[83],"that":[84,95],"are":[85],"descriptive":[86],"important":[88],"examined":[91],"corpus.":[92],"Experiments":[93],"show":[94],"technique":[98],"greatly":[99],"improves":[100],"over":[101],"baseline":[103],"approach,":[104],"both":[105],"terms":[107],"F-measure":[109],"entropy":[111],"on":[112,119],"one":[114],"hand":[115],"computational":[117],"cost":[118],"other.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}