{"id":"https://openalex.org/W3198975419","doi":"https://doi.org/10.1093/llc/fqab032","title":"A data-driven approach to studying changing vocabularies in historical newspaper collections","display_name":"A data-driven approach to studying changing vocabularies in historical newspaper collections","publication_year":2021,"publication_date":"2021-03-24","ids":{"openalex":"https://openalex.org/W3198975419","doi":"https://doi.org/10.1093/llc/fqab032","mag":"3198975419"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqab032","is_oa":true,"landing_page_url":"https://doi.org/10.1093/llc/fqab032","pdf_url":"https://academic.oup.com/dsh/article-pdf/36/Supplement_2/ii109/41091152/fqab032.pdf","source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/dsh/article-pdf/36/Supplement_2/ii109/41091152/fqab032.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006297499","display_name":"Simon Hengchen","orcid":"https://orcid.org/0000-0002-8453-7221"},"institutions":[{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Simon Hengchen","raw_affiliation_strings":["Spr\u00e5kbanken Text, University of Gothenburg, Sweden and iguanodon.ai, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-8453-7221","affiliations":[{"raw_affiliation_string":"Spr\u00e5kbanken Text, University of Gothenburg, Sweden and iguanodon.ai, Belgium","institution_ids":["https://openalex.org/I881427289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046911214","display_name":"Ruben Ros","orcid":"https://orcid.org/0000-0002-5303-2861"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Ruben Ros","raw_affiliation_strings":["Centre for Contemporary and Digital History (C2DH), University of Luxembourg, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0002-5303-2861","affiliations":[{"raw_affiliation_string":"Centre for Contemporary and Digital History (C2DH), University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027019518","display_name":"Jani Marjanen","orcid":"https://orcid.org/0000-0002-3085-4862"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I2800229700","display_name":"Helsinki Institute of Physics","ror":"https://ror.org/01x2x1522","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I2800229700","https://openalex.org/I63548447","https://openalex.org/I94722563","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jani Marjanen","raw_affiliation_strings":["Helsinki Computational History Group, University of Helsinki, Finland "],"raw_orcid":"https://orcid.org/0000-0002-3085-4862","affiliations":[{"raw_affiliation_string":"Helsinki Computational History Group, University of Helsinki, Finland ","institution_ids":["https://openalex.org/I133731052","https://openalex.org/I2800229700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080296686","display_name":"Mikko Tolonen","orcid":"https://orcid.org/0000-0003-2892-8911"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Tolonen","raw_affiliation_strings":["Helsinki Computational History Group, University of Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0003-2892-8911","affiliations":[{"raw_affiliation_string":"Helsinki Computational History Group, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006297499"],"corresponding_institution_ids":["https://openalex.org/I881427289"],"apc_list":{"value":2522,"currency":"GBP","value_usd":3093},"apc_paid":{"value":2522,"currency":"GBP","value_usd":3093},"fwci":16.0479,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.9887436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"36","issue":"Supplement_2","first_page":"ii109","last_page":"ii126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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":0.9585000276565552,"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/newspaper","display_name":"Newspaper","score":0.7772833108901978},{"id":"https://openalex.org/keywords/vagueness","display_name":"Vagueness","score":0.7019379734992981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6342175006866455},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5539848804473877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49340978264808655},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4733058512210846},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4585222601890564},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45139098167419434},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4469906687736511},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.446300745010376},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4409671425819397},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.41480162739753723},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.1297447383403778}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.7772833108901978},{"id":"https://openalex.org/C2776825360","wikidata":"https://www.wikidata.org/wiki/Q1411921","display_name":"Vagueness","level":3,"score":0.7019379734992981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6342175006866455},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5539848804473877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49340978264808655},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4733058512210846},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4585222601890564},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45139098167419434},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4469906687736511},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.446300745010376},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4409671425819397},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.41480162739753723},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.1297447383403778},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C29595303","wikidata":"https://www.wikidata.org/wiki/Q165650","display_name":"Media studies","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/llc/fqab032","is_oa":true,"landing_page_url":"https://doi.org/10.1093/llc/fqab032","pdf_url":"https://academic.oup.com/dsh/article-pdf/36/Supplement_2/ii109/41091152/fqab032.pdf","source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},{"id":"pmh:oai:helda.helsinki.fi:10138/336216","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/336216","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1093/llc/fqab032","is_oa":true,"landing_page_url":"https://doi.org/10.1093/llc/fqab032","pdf_url":"https://academic.oup.com/dsh/article-pdf/36/Supplement_2/ii109/41091152/fqab032.pdf","source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1145621603","display_name":null,"funder_award_id":"2019-2022","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G4418625073","display_name":null,"funder_award_id":"2018-01184","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G5032044671","display_name":"NewsEye: A Digital Investigator for Historical Newspapers","funder_award_id":"770299","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G712881263","display_name":null,"funder_award_id":"2018-","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G7199227476","display_name":null,"funder_award_id":"2019-2022","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G8058219222","display_name":null,"funder_award_id":"2019-2022","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321097","display_name":"Kela","ror":"https://ror.org/057yw0190"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3198975419.pdf","grobid_xml":"https://content.openalex.org/works/W3198975419.grobid-xml"},"referenced_works_count":88,"referenced_works":["https://openalex.org/W108736092","https://openalex.org/W145814658","https://openalex.org/W158861739","https://openalex.org/W203864031","https://openalex.org/W656672532","https://openalex.org/W751409110","https://openalex.org/W1505571847","https://openalex.org/W1544443984","https://openalex.org/W1555649551","https://openalex.org/W1569063737","https://openalex.org/W1605093565","https://openalex.org/W1965403461","https://openalex.org/W1976419325","https://openalex.org/W2000360308","https://openalex.org/W2012499023","https://openalex.org/W2014652847","https://openalex.org/W2022000756","https://openalex.org/W2028160392","https://openalex.org/W2031497137","https://openalex.org/W2034474463","https://openalex.org/W2053921957","https://openalex.org/W2072644219","https://openalex.org/W2101234009","https://openalex.org/W2121393013","https://openalex.org/W2165232124","https://openalex.org/W2169562342","https://openalex.org/W2171343266","https://openalex.org/W2239278652","https://openalex.org/W2307020448","https://openalex.org/W2316251265","https://openalex.org/W2322211782","https://openalex.org/W2332086051","https://openalex.org/W2332216056","https://openalex.org/W2342875884","https://openalex.org/W2399378566","https://openalex.org/W2407585195","https://openalex.org/W2579493205","https://openalex.org/W2583135916","https://openalex.org/W2597289420","https://openalex.org/W2612623103","https://openalex.org/W2759556264","https://openalex.org/W2766641435","https://openalex.org/W2787132789","https://openalex.org/W2789202651","https://openalex.org/W2789452164","https://openalex.org/W2882319491","https://openalex.org/W2891035694","https://openalex.org/W2891069910","https://openalex.org/W2904245610","https://openalex.org/W2910465902","https://openalex.org/W2913798560","https://openalex.org/W2924489021","https://openalex.org/W2946980195","https://openalex.org/W2950133940","https://openalex.org/W2952145453","https://openalex.org/W2963308321","https://openalex.org/W2963780471","https://openalex.org/W2971026089","https://openalex.org/W2972724002","https://openalex.org/W2972893188","https://openalex.org/W2977687816","https://openalex.org/W2979401726","https://openalex.org/W2981601816","https://openalex.org/W3000445156","https://openalex.org/W3012289950","https://openalex.org/W3046690594","https://openalex.org/W3080782212","https://openalex.org/W3104389660","https://openalex.org/W3121771710","https://openalex.org/W3124095375","https://openalex.org/W3137245718","https://openalex.org/W3216404684","https://openalex.org/W4210706177","https://openalex.org/W4240952910","https://openalex.org/W4294170691","https://openalex.org/W4301753339","https://openalex.org/W6605936340","https://openalex.org/W6606475831","https://openalex.org/W6668529637","https://openalex.org/W6675354045","https://openalex.org/W6682691769","https://openalex.org/W6691445387","https://openalex.org/W6699494303","https://openalex.org/W6712774035","https://openalex.org/W6732424254","https://openalex.org/W6746317852","https://openalex.org/W6750041411","https://openalex.org/W6769430610"],"related_works":["https://openalex.org/W2251084681","https://openalex.org/W287510790","https://openalex.org/W2098784136","https://openalex.org/W2130795788","https://openalex.org/W2968543375","https://openalex.org/W2571817549","https://openalex.org/W1541975828","https://openalex.org/W2159336305","https://openalex.org/W2987141700","https://openalex.org/W2953770453"],"abstract_inverted_index":{"Abstract":[0],"Nation":[1],"and":[2,24,45,93,107,148,215],"nationhood":[3],"are":[4,28,113],"among":[5],"the":[6,12,18,21,53,56,66,83,98,101,119,122,137,186,202],"most":[7],"frequently":[8],"studied":[9],"concepts":[10],"in":[11,33,55,144,171,178,190,218],"field":[13],"of":[14,52,58,79,85,100,121,139,162,185,204],"intellectual":[15],"history.":[16],"At":[17],"same":[19],"time,":[20],"word":[22,47,91],"\u2018nation\u2019":[23],"its":[25],"historical":[26,141],"usage":[27],"very":[29],"vague.":[30],"The":[31],"aim":[32],"this":[34,59,62,163,191],"article":[35,192],"was":[36],"to":[37,49,82,96,136,167,201,211],"develop":[38],"a":[39,76,179],"data-driven":[40,180],"method":[41,187],"using":[42,71],"dependency":[43],"parsing":[44],"neural":[46],"embeddings":[48,92],"clarify":[50],"some":[51],"vagueness":[54],"evolution":[57],"concept.":[60],"To":[61,117,150],"end,":[63],"we":[64,74,88,133,188],"propose":[65],"following":[67],"two-step":[68],"method.":[69],"First,":[70],"linguistic":[72],"processing,":[73],"create":[75,109],"large":[77,131],"set":[78],"words":[80,106],"pertaining":[81],"topic":[84],"nation.":[86],"Second,":[87],"train":[89],"diachronic":[90],"use":[94],"them":[95],"quantify":[97],"strength":[99,184],"semantic":[102],"similarity":[103],"between":[104],"these":[105],"thereby":[108],"meaningful":[110],"clusters,":[111],"which":[112],"then":[114],"aligned":[115],"diachronically.":[116],"illustrate":[118],"robustness":[120],"study":[123,203],"across":[124],"languages,":[125],"time":[126],"spans,":[127],"as":[128,130,172,174],"well":[129],"datasets,":[132],"apply":[134],"it":[135,197,210],"entirety":[138],"five":[140],"newspaper":[142],"archives":[143],"Dutch,":[145],"Swedish,":[146],"Finnish,":[147],"English.":[149],"our":[151],"knowledge,":[152],"thus":[153],"far":[154],"there":[155],"have":[156],"been":[157],"no":[158],"large-scale":[159],"comparative":[160],"studies":[161],"kind":[164],"that":[165],"purport":[166],"grasp":[168],"long-term":[169],"developments":[170],"many":[173],"four":[175],"different":[176,219],"languages":[177],"way.":[181],"A":[182],"particular":[183],"describe":[189],"is":[193,198,216],"that,":[194],"by":[195],"design,":[196],"not":[199],"limited":[200],"nationhood,":[205],"but":[206],"rather":[207],"expands":[208],"beyond":[209],"other":[212],"research":[213],"questions":[214],"reusable":[217],"contexts.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
