{"id":"https://openalex.org/W4312091612","doi":"https://doi.org/10.1093/llc/fqac079","title":"Creating specialized corpora from digitized historical newspaper archives","display_name":"Creating specialized corpora from digitized historical newspaper archives","publication_year":2022,"publication_date":"2022-12-22","ids":{"openalex":"https://openalex.org/W4312091612","doi":"https://doi.org/10.1093/llc/fqac079"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqac079","is_oa":true,"landing_page_url":"https://doi.org/10.1093/llc/fqac079","pdf_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqac079/48353105/fqac079.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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqac079/48353105/fqac079.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078517609","display_name":"Joshua Wilson Black","orcid":"https://orcid.org/0000-0002-8272-5763"},"institutions":[{"id":"https://openalex.org/I185492890","display_name":"University of Canterbury","ror":"https://ror.org/03y7q9t39","country_code":"NZ","type":"education","lineage":["https://openalex.org/I185492890"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Joshua Wilson Black","raw_affiliation_strings":["New Zealand Institute of Language, Brain and Behaviour, University of Canterbury , Christchurch, New Zealand","UC Arts Digital Lab, University of Canterbury , Christchurch, New Zealand"],"raw_orcid":"https://orcid.org/0000-0002-8272-5763","affiliations":[{"raw_affiliation_string":"New Zealand Institute of Language, Brain and Behaviour, University of Canterbury , Christchurch, New Zealand","institution_ids":["https://openalex.org/I185492890"]},{"raw_affiliation_string":"UC Arts Digital Lab, University of Canterbury , Christchurch, New Zealand","institution_ids":["https://openalex.org/I185492890"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078517609"],"corresponding_institution_ids":["https://openalex.org/I185492890"],"apc_list":{"value":2522,"currency":"GBP","value_usd":3093},"apc_paid":null,"fwci":3.0566,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93938613,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"38","issue":"2","first_page":"779","last_page":"797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9909999966621399,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9811000227928162,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.920872688293457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262711524963379},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6260495781898499},{"id":"https://openalex.org/keywords/digital-archives","display_name":"Digital Archives","score":0.6080857515335083},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5947567820549011},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4989149570465088},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.45356816053390503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45003315806388855},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41193029284477234},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.26092666387557983},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12214413285255432},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09076812863349915}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.920872688293457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262711524963379},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6260495781898499},{"id":"https://openalex.org/C2780157182","wikidata":"https://www.wikidata.org/wiki/Q11154625","display_name":"Digital Archives","level":2,"score":0.6080857515335083},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5947567820549011},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4989149570465088},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.45356816053390503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45003315806388855},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41193029284477234},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26092666387557983},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12214413285255432},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09076812863349915},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/llc/fqac079","is_oa":true,"landing_page_url":"https://doi.org/10.1093/llc/fqac079","pdf_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqac079/48353105/fqac079.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1093/llc/fqac079","is_oa":true,"landing_page_url":"https://doi.org/10.1093/llc/fqac079","pdf_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqac079/48353105/fqac079.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310502","display_name":"University of Canterbury","ror":"https://ror.org/03y7q9t39"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312091612.pdf","grobid_xml":"https://content.openalex.org/works/W4312091612.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W28080241","https://openalex.org/W1492815834","https://openalex.org/W1495358526","https://openalex.org/W1502732847","https://openalex.org/W1515238108","https://openalex.org/W1521626219","https://openalex.org/W1536133480","https://openalex.org/W1574968832","https://openalex.org/W1716486257","https://openalex.org/W1825514821","https://openalex.org/W1871425179","https://openalex.org/W1880262756","https://openalex.org/W1890785255","https://openalex.org/W1965719558","https://openalex.org/W1976457731","https://openalex.org/W2013998579","https://openalex.org/W2040799618","https://openalex.org/W2049873434","https://openalex.org/W2101234009","https://openalex.org/W2153852638","https://openalex.org/W2153895776","https://openalex.org/W2249004193","https://openalex.org/W2386972674","https://openalex.org/W2585068927","https://openalex.org/W2623304523","https://openalex.org/W2760665663","https://openalex.org/W2782848721","https://openalex.org/W2800652486","https://openalex.org/W2901924367","https://openalex.org/W2948202728","https://openalex.org/W2979666134","https://openalex.org/W2995864995","https://openalex.org/W3022091105","https://openalex.org/W3039922271","https://openalex.org/W3081407480","https://openalex.org/W3083917661","https://openalex.org/W4211034239","https://openalex.org/W4211148787","https://openalex.org/W4234376047","https://openalex.org/W4236353546","https://openalex.org/W4243754476","https://openalex.org/W4248914187","https://openalex.org/W4310711452","https://openalex.org/W6624890885","https://openalex.org/W6629968793","https://openalex.org/W6630749671","https://openalex.org/W6639242060","https://openalex.org/W6639619044","https://openalex.org/W6653878544","https://openalex.org/W6674373024","https://openalex.org/W6675354045","https://openalex.org/W6691472082","https://openalex.org/W6710875753","https://openalex.org/W6782753689"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W2100945520","https://openalex.org/W2386525189","https://openalex.org/W2772005286","https://openalex.org/W2288740233"],"abstract_inverted_index":{"Abstract":[0],"The":[1,101,138],"availability":[2],"of":[3,7,19,27,51,57],"large":[4,74],"digital":[5,46],"archives":[6,21,75,91],"historical":[8,14,89],"newspaper":[9,90],"content":[10],"has":[11],"transformed":[12],"the":[13,17,24,49,58,60,94],"sciences.":[15],"However,":[16],"scale":[18],"these":[20],"can":[22],"limit":[23],"direct":[25],"application":[26],"advanced":[28],"text":[29,115,125],"processing":[30,42],"methods.":[31],"Even":[32],"if":[33,48],"it":[34],"is":[35,53,103,140,160],"computationally":[36],"feasible":[37],"to":[38,43,64,78,133],"apply":[39],"sophisticated":[40],"language":[41],"an":[44,104],"entire":[45],"archive,":[47,59],"material":[50],"interest":[52],"a":[54,86,143],"small":[55],"fraction":[56],"results":[61],"are":[62,76,112,119,127],"unlikely":[63],"be":[65],"useful.":[66],"Methods":[67],"for":[68,88],"generating":[69],"smaller":[70],"specialized":[71],"corpora":[72,111],"from":[73],"required":[77],"solve":[79],"this":[80],"problem.":[81],"This":[82],"article":[83],"presents":[84],"such":[85],"method":[87,102,139],"digitized":[92],"using":[93,114],"METS/ALTO":[95],"XML":[96],"standard":[97],"(Veridian":[98],"Software,":[99],"n.d.).":[100],"\u2018iterative":[105],"bootstrapping\u2019":[106],"approach":[107],"in":[108,131,152,162],"which":[109],"candidate":[110,136],"evaluated":[113],"mining":[116],"techniques,":[117],"items":[118],"manually":[120],"labelled,":[121],"and":[122,129],"Na\u00efve":[123],"Bayes":[124],"classifiers":[126],"trained":[128],"applied":[130],"order":[132],"produce":[134],"new":[135],"corpora.":[137],"illustrated":[141],"by":[142],"case":[144],"study":[145],"that":[146],"investigates":[147],"philosophical":[148],"content,":[149],"broadly":[150],"construed,":[151],"pre-1900":[153],"English-language":[154],"New":[155],"Zealand":[156],"newspapers.":[157],"Extensive":[158],"code":[159],"provided":[161],"Supplementary":[163],"Materials.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
