{"id":"https://openalex.org/W7140072464","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.19","title":"WikiLingDiv: a dataset for quantifying digital linguistic diversity using Wikipedia page views","display_name":"WikiLingDiv: a dataset for quantifying digital linguistic diversity using Wikipedia page views","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140072464","doi":"https://doi.org/10.18653/v1/2026.latechclfl-1.19"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.19","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.19","pdf_url":"https://aclanthology.org/2026.latechclfl-1.19.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.latechclfl-1.19.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120451432","display_name":"Hannes Essfors","orcid":"https://orcid.org/0009-0002-7419-9713"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Hannes Essfors","raw_affiliation_strings":["TU Wien Informatics , Favoritenstra\u00dfe 9-11 , 1040 Vienna , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien Informatics , Favoritenstra\u00dfe 9-11 , 1040 Vienna , Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146779818","display_name":"Andreas Baumann","orcid":null},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Andreas Baumann","raw_affiliation_strings":["Faculty of Philological and Cultural Studies , University of Vienna , Universit\u00e4tsring 1 , 1010 Vienna , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Philological and Cultural Studies , University of Vienna , Universit\u00e4tsring 1 , 1010 Vienna , Austria","institution_ids":["https://openalex.org/I129774422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19890511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"202","last_page":"211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.7861999869346619,"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"}},"topics":[{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.7861999869346619,"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"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.04600000008940697,"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":0.025299999862909317,"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/diversity","display_name":"Diversity (politics)","score":0.4627000093460083},{"id":"https://openalex.org/keywords/linguistic-diversity","display_name":"Linguistic diversity","score":0.35600000619888306},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.30649998784065247},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.25200000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589000225067139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5221999883651733},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5016000270843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46540001034736633},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C2992249680","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Linguistic diversity","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.latechclfl-1.19","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.19","pdf_url":"https://aclanthology.org/2026.latechclfl-1.19.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.latechclfl-1.19","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.latechclfl-1.19","pdf_url":"https://aclanthology.org/2026.latechclfl-1.19.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4068663716316223,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321003","display_name":"Vienna Science and Technology Fund","ror":"https://ror.org/01f9mc681"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140072464.pdf","grobid_xml":"https://content.openalex.org/works/W7140072464.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,33,89,121,140],"conflation":[2],"of":[3,17,19,62,73,77,97],"digital":[4,34,63,98,137,151],"and":[5,8,83,94,107,111,127,139,150],"non-digital":[6],"spaces,":[7],"NLP":[9],"technologies":[10],"being":[11],"integrated":[12],"into":[13],"an":[14,42,124],"increasing":[15],"number":[16],"aspects":[18],"daily":[20],"life,":[21],"linguistic":[22,48,64,99,148],"diversity":[23,49,103],"cannot":[24],"be":[25],"fully":[26],"understood":[27],"without":[28],"considering":[29],"language":[30,75,118],"use":[31],"in":[32,50,117,134],"space.To":[35],"facilitate":[36],"such":[37],"research,":[38],"we":[39,91],"introduce":[40],"WikiLingDiv,":[41],"openly":[43,125],"accessible":[44],"dataset":[45,66,122],"for":[46,132],"quantifying":[47],"online":[51],"knowledge":[52],"retrieval":[53],"using":[54],"Wikipedia":[55],"page":[56,71],"views,":[57],"corresponding":[58],"to":[59],"one":[60],"dimension":[61],"diversity.Our":[65],"is":[67],"based":[68],"on":[69,147],"yearly":[70],"views":[72],"340":[74],"editions":[76],"Wikipedia,":[78],"aggregated":[79],"across":[80,109],"239":[81],"countries":[82,110],"territories":[84],"over":[85],"10":[86],"years":[87],"(2015)(2016)(2017)(2018)(2019)(2020)(2021)(2022)(2023)(2024).Using":[88],"dataset,":[90],"illustrate":[92],"spatial":[93],"temporal":[95],"patterns":[96],"diversity,":[100],"suggesting":[101],"that":[102],"has":[104],"both":[105],"increased":[106],"decreased":[108],"regions,":[112],"while":[113],"highlighting":[114],"country-specific":[115],"dynamics":[116],"usage.We":[119],"release":[120],"as":[123],"available":[126],"easily":[128],"integrable":[129],"data":[130],"resource":[131],"researchers":[133],"computational":[135],"linguistics,":[136],"humanities,":[138],"broader":[141],"social":[142],"sciences,":[143],"enabling":[144],"further":[145],"work":[146],"variation":[149],"inequality.":[152]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-03-11T00:00:00"}
