{"id":"https://openalex.org/W3113998794","doi":"https://doi.org/10.1162/qss_a_00105","title":"Wikipedia citations: A comprehensive data set of citations with identifiers extracted from English Wikipedia","display_name":"Wikipedia citations: A comprehensive data set of citations with identifiers extracted from English Wikipedia","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3113998794","doi":"https://doi.org/10.1162/qss_a_00105","mag":"3113998794"},"language":"en","primary_location":{"id":"doi:10.1162/qss_a_00105","is_oa":true,"landing_page_url":"https://doi.org/10.1162/qss_a_00105","pdf_url":"https://direct.mit.edu/qss/article-pdf/2/1/1/1906624/qss_a_00105.pdf","source":{"id":"https://openalex.org/S4210195326","display_name":"Quantitative Science Studies","issn_l":"2641-3337","issn":["2641-3337"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantitative Science Studies","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://direct.mit.edu/qss/article-pdf/2/1/1/1906624/qss_a_00105.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087117411","display_name":"Harshdeep Singh","orcid":"https://orcid.org/0000-0002-0517-1576"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Harshdeep Singh","raw_affiliation_strings":["Data Science Laboratory, EPFL"],"affiliations":[{"raw_affiliation_string":"Data Science Laboratory, EPFL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101446790","display_name":"Robert West","orcid":"https://orcid.org/0000-0002-3984-1232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert West","raw_affiliation_strings":["Data Science Laboratory, EPFL"],"affiliations":[{"raw_affiliation_string":"Data Science Laboratory, EPFL","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005227218","display_name":"Giovanni Colavizza","orcid":"https://orcid.org/0000-0002-9806-084X"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Giovanni Colavizza","raw_affiliation_strings":["Institute for Logic, Language and Computation, University of Amsterdam","Institute for Logic, Language and Computation, University of\n Amsterdam"],"affiliations":[{"raw_affiliation_string":"Institute for Logic, Language and Computation, University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Institute for Logic, Language and Computation, University of\n Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087117411"],"corresponding_institution_ids":[],"apc_list":{"value":800,"currency":"USD","value_usd":800},"apc_paid":{"value":800,"currency":"USD","value_usd":800},"fwci":9.1624,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.97891635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9498000144958496,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9205999970436096,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6775046586990356},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6239431500434875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6055940389633179},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.6014081835746765},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5459668636322021},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5330411791801453},{"id":"https://openalex.org/keywords/cites","display_name":"CITES","score":0.4121280610561371},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.347348153591156}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6775046586990356},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6239431500434875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6055940389633179},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.6014081835746765},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5459668636322021},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5330411791801453},{"id":"https://openalex.org/C95803793","wikidata":"https://www.wikidata.org/wiki/Q191836","display_name":"CITES","level":2,"score":0.4121280610561371},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.347348153591156},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C505870484","wikidata":"https://www.wikidata.org/wiki/Q180538","display_name":"Fishery","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1162/qss_a_00105","is_oa":true,"landing_page_url":"https://doi.org/10.1162/qss_a_00105","pdf_url":"https://direct.mit.edu/qss/article-pdf/2/1/1/1906624/qss_a_00105.pdf","source":{"id":"https://openalex.org/S4210195326","display_name":"Quantitative Science Studies","issn_l":"2641-3337","issn":["2641-3337"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantitative Science Studies","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:openaire/99f8daa5-02eb-41e0-a84e-89a91b271ab6","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/wikipedia-citations-a-comprehensive-data-set-of-citations-with-identifiers-extracted-from-english-wikipedia(99f8daa5-02eb-41e0-a84e-89a91b271ab6).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Singh, H, West, R & Colavizza, G 2021, 'Wikipedia citations: A comprehensive data set of citations with identifiers extracted from English Wikipedia', Quantitative Science Studies, vol. 2, no. 1, pp. 1-19. https://doi.org/10.1162/qss_a_00105","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:cris.unibo.it:11585/948750","is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/948750","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:dare.uva.nl:publications/99f8daa5-02eb-41e0-a84e-89a91b271ab6","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/99f8daa5-02eb-41e0-a84e-89a91b271ab6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Singh, H, West, R & Colavizza, G 2021, 'Wikipedia citations: A comprehensive data set of citations with identifiers extracted from English Wikipedia', Quantitative Science Studies, vol. 2, no. 1, pp. 1-19. https://doi.org/10.1162/qss_a_00105","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:c4230c7d80f54d11a8b402c06c6696b3","is_oa":true,"landing_page_url":"https://doaj.org/article/c4230c7d80f54d11a8b402c06c6696b3","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Quantitative Science Studies, Vol 2, Iss 1, Pp 1-19 (2021)","raw_type":"article"},{"id":"pmh:oai:infoscience.epfl.ch:289168","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/289168","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"research article"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/99f8daa5-02eb-41e0-a84e-89a91b271ab6","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/wikipedia-citations-a-comprehensive-data-set-of-citations-with-identifiers-extracted-from-english-wikipedia(99f8daa5-02eb-41e0-a84e-89a91b271ab6).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Quantitative Science Studies, 2(1), 1 - 19. MIT Press Journals","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1162/qss_a_00105","is_oa":true,"landing_page_url":"https://doi.org/10.1162/qss_a_00105","pdf_url":"https://direct.mit.edu/qss/article-pdf/2/1/1/1906624/qss_a_00105.pdf","source":{"id":"https://openalex.org/S4210195326","display_name":"Quantitative Science Studies","issn_l":"2641-3337","issn":["2641-3337"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Quantitative Science Studies","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320312538","display_name":"Wikimedia Foundation","ror":"https://ror.org/032q98j12"},{"id":"https://openalex.org/F4320320915","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052"},{"id":"https://openalex.org/F4320320929","display_name":"Universiteit Leiden","ror":"https://ror.org/027bh9e22"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3113998794.pdf","grobid_xml":"https://content.openalex.org/works/W3113998794.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W133299927","https://openalex.org/W1522301498","https://openalex.org/W1552847225","https://openalex.org/W1553564559","https://openalex.org/W1575756813","https://openalex.org/W1586276670","https://openalex.org/W1808807089","https://openalex.org/W1971087125","https://openalex.org/W1972067873","https://openalex.org/W1995450124","https://openalex.org/W2007232175","https://openalex.org/W2073018527","https://openalex.org/W2081116169","https://openalex.org/W2082603871","https://openalex.org/W2116190778","https://openalex.org/W2118925472","https://openalex.org/W2120064173","https://openalex.org/W2131774270","https://openalex.org/W2143493069","https://openalex.org/W2152303055","https://openalex.org/W2296235651","https://openalex.org/W2338981077","https://openalex.org/W2339384895","https://openalex.org/W2340254858","https://openalex.org/W2426372034","https://openalex.org/W2486591191","https://openalex.org/W2493916176","https://openalex.org/W2518646621","https://openalex.org/W2524182563","https://openalex.org/W2531946635","https://openalex.org/W2599784308","https://openalex.org/W2612309901","https://openalex.org/W2620867994","https://openalex.org/W2741737307","https://openalex.org/W2745405023","https://openalex.org/W2752070947","https://openalex.org/W2754096738","https://openalex.org/W2761728857","https://openalex.org/W2767995756","https://openalex.org/W2776490793","https://openalex.org/W2911641747","https://openalex.org/W2924113343","https://openalex.org/W2937233437","https://openalex.org/W2952239097","https://openalex.org/W2963647183","https://openalex.org/W2970217669","https://openalex.org/W2972182717","https://openalex.org/W3000895385","https://openalex.org/W3004537452","https://openalex.org/W3008649179","https://openalex.org/W3009541245","https://openalex.org/W3021826561","https://openalex.org/W3023758415","https://openalex.org/W3042565502","https://openalex.org/W3044875688","https://openalex.org/W3092431853","https://openalex.org/W3101883599","https://openalex.org/W3102513619","https://openalex.org/W3102617929","https://openalex.org/W3105900399","https://openalex.org/W3113998794","https://openalex.org/W3125256337","https://openalex.org/W4394427106","https://openalex.org/W6608540991","https://openalex.org/W6633077404","https://openalex.org/W6670810200","https://openalex.org/W6743638035","https://openalex.org/W6743750934","https://openalex.org/W6767015159","https://openalex.org/W6864187837","https://openalex.org/W6941209911"],"related_works":["https://openalex.org/W2436357665","https://openalex.org/W4232717460","https://openalex.org/W2022702306","https://openalex.org/W255791531","https://openalex.org/W2387286477","https://openalex.org/W1969556972","https://openalex.org/W3009094716","https://openalex.org/W3123951218","https://openalex.org/W4251832544","https://openalex.org/W2892255863"],"abstract_inverted_index":{"Abstract":[0],"Wikipedia\u2019s":[1],"content":[2],"is":[3,15,32],"based":[4],"on":[5],"reliable":[6],"and":[7,28,65,93,126,158],"published":[8],"sources.":[9],"To":[10,34],"this":[11,36],"date,":[12],"relatively":[13],"little":[14],"known":[16,88],"about":[17],"what":[18],"sources":[19,31],"Wikipedia":[20,40,59,114,128],"relies":[21],"on,":[22],"in":[23,140,163],"part":[24],"because":[25],"extracting":[26],"citations":[27,47,54,83,101],"identifying":[29],"cited":[30],"challenging.":[33],"close":[35],"gap,":[37],"we":[38,109],"release":[39,146],"Citations,":[41],"a":[42,107,136],"comprehensive":[43],"data":[44,161],"set":[45,162],"of":[46,62,113,132,143],"extracted":[48],"from":[49,55,104],"Wikipedia.":[50],"We":[51,75,145],"extracted29.3":[52],"million":[53,57,82],"6.1":[56],"English":[58],"articles":[60,115,134],"as":[61,67],"May":[63],"2020,":[64],"classified":[66],"being":[68],"books,":[69],"journal":[70,120],"articles,":[71],"or":[72],"Web":[73,142],"content.":[74],"were":[76],"thus":[77],"able":[78],"to":[79,84,149,153],"extract":[80],"4.0":[81],"scholarly":[85],"publications":[86],"with":[87,102,122,135],"identifiers\u2014including":[89],"DOI,":[90,125],"PMC,":[91],"PMID,":[92],"ISBN\u2014and":[94],"further":[95],"equip":[96],"an":[97,123],"extra":[98],"261":[99],"thousand":[100],"DOIs":[103],"Crossref.":[105],"As":[106],"result,":[108],"find":[110],"that":[111,127],"6.7%":[112],"cite":[116],"at":[117],"least":[118],"one":[119],"article":[121],"associated":[124],"cites":[129],"just":[130],"2%":[131],"all":[133],"DOI":[137],"currently":[138],"indexed":[139],"the":[141,151,160,164],"Science.":[144],"our":[147,156],"code":[148],"allow":[150],"community":[152],"extend":[154],"upon":[155],"work":[157],"update":[159],"future.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2021-01-05T00:00:00"}
