{"id":"https://openalex.org/W4377027746","doi":"https://doi.org/10.1017/s1351324923000244","title":"A comparison of latent semantic analysis and correspondence analysis of document-term matrices","display_name":"A comparison of latent semantic analysis and correspondence analysis of document-term matrices","publication_year":2023,"publication_date":"2023-05-18","ids":{"openalex":"https://openalex.org/W4377027746","doi":"https://doi.org/10.1017/s1351324923000244"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324923000244","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000244","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/96316CBB94CD9DD681CB50D9F52E0201/S1351324923000244a.pdf/div-class-title-a-comparison-of-latent-semantic-analysis-and-correspondence-analysis-of-document-term-matrices-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/96316CBB94CD9DD681CB50D9F52E0201/S1351324923000244a.pdf/div-class-title-a-comparison-of-latent-semantic-analysis-and-correspondence-analysis-of-document-term-matrices-div.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101620144","display_name":"Qianqian Qi","orcid":"https://orcid.org/0000-0003-1058-476X"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Qianqian Qi","raw_affiliation_strings":["Department of Methodology and Statistics, Faculty of Social Sciences, Utrecht University, Utrecht, the Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1058-476X","affiliations":[{"raw_affiliation_string":"Department of Methodology and Statistics, Faculty of Social Sciences, Utrecht University, Utrecht, the Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066262383","display_name":"David J. Hessen","orcid":"https://orcid.org/0000-0003-4463-2555"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"David J. Hessen","raw_affiliation_strings":["Department of Methodology and Statistics, Faculty of Social Sciences, Utrecht University, Utrecht, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Methodology and Statistics, Faculty of Social Sciences, Utrecht University, Utrecht, the Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032425412","display_name":"Tejaswini Deoskar","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tejaswini Deoskar","raw_affiliation_strings":["Department of Languages, Literature, and Communication, Faculty of Humanities, Utrecht University, Utrecht, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Languages, Literature, and Communication, Faculty of Humanities, Utrecht University, Utrecht, the Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090384758","display_name":"P.G.M. van der Heijden","orcid":"https://orcid.org/0000-0002-3345-096X"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]},{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Peter G. M. van der Heijden","raw_affiliation_strings":["Department of Methodology and Statistics, Faculty of Social Sciences, Utrecht University, Utrecht, the Netherlands","Southampton Statistical Sciences Research Institute, University of Southampton, Highfield, Southampton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Methodology and Statistics, Faculty of Social Sciences, Utrecht University, Utrecht, the Netherlands","institution_ids":["https://openalex.org/I193662353"]},{"raw_affiliation_string":"Southampton Statistical Sciences Research Institute, University of Southampton, Highfield, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101620144"],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":null,"apc_paid":null,"fwci":2.4411,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90957716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"30","issue":"4","first_page":"722","last_page":"752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","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/T12380","display_name":"Authorship Attribution and Profiling","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":0.9968000054359436,"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":0.9932000041007996,"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/computer-science","display_name":"Computer science","score":0.791289210319519},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.7894479036331177},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6454826593399048},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5883750915527344},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5565434098243713},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.5353980660438538},{"id":"https://openalex.org/keywords/correspondence-analysis","display_name":"Correspondence analysis","score":0.4498429298400879},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44179975986480713},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42964062094688416},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4125659763813019},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.41210103034973145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40546345710754395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18477237224578857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791289210319519},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.7894479036331177},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6454826593399048},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5883750915527344},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5565434098243713},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.5353980660438538},{"id":"https://openalex.org/C148298330","wikidata":"https://www.wikidata.org/wiki/Q1784754","display_name":"Correspondence analysis","level":2,"score":0.4498429298400879},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44179975986480713},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42964062094688416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4125659763813019},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.41210103034973145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40546345710754395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18477237224578857},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324923000244","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000244","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/96316CBB94CD9DD681CB50D9F52E0201/S1351324923000244a.pdf/div-class-title-a-comparison-of-latent-semantic-analysis-and-correspondence-analysis-of-document-term-matrices-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:eprints.soton.ac.uk:455888","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.soton.ac.uk/455888/2/add_today_Fri_15th.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1017/s1351324923000244","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000244","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/96316CBB94CD9DD681CB50D9F52E0201/S1351324923000244a.pdf/div-class-title-a-comparison-of-latent-semantic-analysis-and-correspondence-analysis-of-document-term-matrices-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4377027746.pdf"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W95280405","https://openalex.org/W134855704","https://openalex.org/W1481656608","https://openalex.org/W1594662659","https://openalex.org/W1615991656","https://openalex.org/W1978394996","https://openalex.org/W1980718821","https://openalex.org/W1983578042","https://openalex.org/W2018881432","https://openalex.org/W2030191381","https://openalex.org/W2033219613","https://openalex.org/W2058616517","https://openalex.org/W2060827968","https://openalex.org/W2063059120","https://openalex.org/W2072773380","https://openalex.org/W2076977679","https://openalex.org/W2080051508","https://openalex.org/W2080237260","https://openalex.org/W2091273188","https://openalex.org/W2129250947","https://openalex.org/W2147152072","https://openalex.org/W2150874198","https://openalex.org/W2167132002","https://openalex.org/W2186423839","https://openalex.org/W2252184199","https://openalex.org/W2307589391","https://openalex.org/W2319576313","https://openalex.org/W2406309402","https://openalex.org/W2417131009","https://openalex.org/W2470484508","https://openalex.org/W2559655401","https://openalex.org/W2588236310","https://openalex.org/W2625924629","https://openalex.org/W2735623276","https://openalex.org/W2790404387","https://openalex.org/W2800549175","https://openalex.org/W2811046698","https://openalex.org/W2928364406","https://openalex.org/W2931234817","https://openalex.org/W2952914835","https://openalex.org/W2974922583","https://openalex.org/W3011554092","https://openalex.org/W3100602110","https://openalex.org/W3146304747","https://openalex.org/W3153228281","https://openalex.org/W3153338002","https://openalex.org/W3155264312","https://openalex.org/W3157670290","https://openalex.org/W3185542754","https://openalex.org/W3204438512","https://openalex.org/W4214606138","https://openalex.org/W4246802270","https://openalex.org/W4250089123","https://openalex.org/W4300882602","https://openalex.org/W6604844978","https://openalex.org/W6605346955","https://openalex.org/W6605660442","https://openalex.org/W6891257270"],"related_works":["https://openalex.org/W2161352064","https://openalex.org/W2172446564","https://openalex.org/W4243530889","https://openalex.org/W3005136920","https://openalex.org/W2886330066","https://openalex.org/W2188432624","https://openalex.org/W2576886807","https://openalex.org/W3004487639","https://openalex.org/W2909504796","https://openalex.org/W4285580183"],"abstract_inverted_index":{"Abstract":[0],"Latent":[1],"semantic":[2],"analysis":[3,7,44],"(LSA)":[4],"and":[5,35,45,81,89,109,120,138,145,169],"correspondence":[6],"(CA)":[8],"are":[9,92],"two":[10,49],"techniques":[11,50],"that":[12,30,59,71,75,96,116,147,173],"use":[13],"a":[14,42,157],"singular":[15],"value":[16],"decomposition":[17],"for":[18,69],"dimensionality":[19],"reduction.":[20],"LSA":[21,121],"has":[22,61],"been":[23],"extensively":[24],"used":[25],"to":[26,67,103,129,156,178],"obtain":[27],"low-dimensional":[28],"representations":[29],"capture":[31],"relationships":[32,106],"among":[33,107,182],"documents":[34,108],"terms.":[36,110],"In":[37],"this":[38],"article,":[39],"we":[40],"present":[41],"theoretical":[43],"comparison":[46],"of":[47,54,73,78,163],"the":[48,52,97,161,164,179],"in":[51,136],"context":[53],"document-term":[55],"matrices.":[56],"We":[57,125,152],"show":[58],"CA":[60,98,119,128,148,155],"some":[62],"attractive":[63],"properties":[64],"as":[65,122],"compared":[66],"LSA,":[68],"instance":[70],"effects":[72],"margins,":[74],"is,":[76],"sums":[77],"row":[79],"elements":[80],"column":[82],"elements,":[83],"arising":[84],"from":[85],"differing":[86],"document":[87],"lengths":[88],"term":[90],"frequencies":[91],"effectively":[93],"eliminated":[94],"so":[95],"solution":[99],"is":[100,114],"optimally":[101],"suited":[102],"focus":[104],"on":[105,133,141],"A":[111],"unifying":[112],"framework":[113],"proposed":[115],"includes":[117],"both":[118],"special":[123],"cases.":[124],"empirically":[126],"compare":[127],"various":[130],"LSA-based":[131],"methods":[132],"text":[134],"categorization":[135],"English":[137],"authorship":[139,162],"attribution":[140],"historical":[142],"Dutch":[143,165],"texts":[144],"find":[146],"performs":[149],"significantly":[150],"better.":[151],"also":[153],"apply":[154],"long-standing":[158],"question":[159],"regarding":[160],"national":[166],"anthem":[167],"Wilhelmus":[168],"provide":[170],"further":[171],"support":[172],"it":[174],"can":[175],"be":[176],"attributed":[177],"author":[180],"Datheen,":[181],"several":[183],"contenders.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}