{"id":"https://openalex.org/W3167712888","doi":"https://doi.org/10.1145/3442442.3452350","title":"Inferring Sociodemographic Attributes of Wikipedia Editors: State-of-the-art and Implications for Editor Privacy","display_name":"Inferring Sociodemographic Attributes of Wikipedia Editors: State-of-the-art and Implications for Editor Privacy","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3167712888","doi":"https://doi.org/10.1145/3442442.3452350","mag":"3167712888"},"language":"en","primary_location":{"id":"doi:10.1145/3442442.3452350","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442442.3452350","pdf_url":null,"source":{"id":"https://openalex.org/S4306506652","display_name":"Companion Proceedings of the Web Conference 2021","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3442442.3452350","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072541586","display_name":"Sebastian Br\u00fcckner","orcid":"https://orcid.org/0000-0001-7699-6201"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sebastian Br\u00fcckner","raw_affiliation_strings":["RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076202690","display_name":"Florian Lemmerich","orcid":"https://orcid.org/0000-0001-7620-1376"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Lemmerich","raw_affiliation_strings":["RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071422618","display_name":"Markus Strohmaier","orcid":"https://orcid.org/0000-0002-5485-5720"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I4210101898","display_name":"GESIS - Leibniz-Institute for the Social Sciences","ror":"https://ror.org/018afyw53","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210101898"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Strohmaier","raw_affiliation_strings":["RWTH Aachen University &amp; GESIS - Leibniz Institute for the Social Sciences, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University &amp; GESIS - Leibniz Institute for the Social Sciences, Germany","institution_ids":["https://openalex.org/I4210101898","https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072541586"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":1.3711,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78867925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"616","last_page":"622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9993000030517578,"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":0.9993000030517578,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9976000189781189,"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/T13157","display_name":"Cancer-related gene regulation","score":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.6733664274215698},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6308099627494812},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5327650904655457},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4920918345451355},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4623070955276489},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41769102215766907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4109210968017578},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.39291155338287354},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38229504227638245},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3424495458602905},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1837795078754425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6733664274215698},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6308099627494812},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5327650904655457},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4920918345451355},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4623070955276489},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41769102215766907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4109210968017578},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.39291155338287354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38229504227638245},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3424495458602905},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1837795078754425},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3442442.3452350","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442442.3452350","pdf_url":null,"source":{"id":"https://openalex.org/S4306506652","display_name":"Companion Proceedings of the Web Conference 2021","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:61550","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401433","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},{"id":"pmh:oai:publications.rwth-aachen.de:841714","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/841714","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Companion Proceedings of the Web Conference 2021 / Edited by Jure Leskovec, Marko Grobelnik, Marc Najork, Jie Tang, Leila Zia<br/>30. Web Conference, WWW 2021, online, 2021-04-19 - 2021-04-23","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3442442.3452350","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442442.3452350","pdf_url":null,"source":{"id":"https://openalex.org/S4306506652","display_name":"Companion Proceedings of the Web Conference 2021","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2086806158","https://openalex.org/W2119595472","https://openalex.org/W2144163256","https://openalex.org/W2148143831","https://openalex.org/W2258528563","https://openalex.org/W2299844149","https://openalex.org/W2540646130","https://openalex.org/W2590878907","https://openalex.org/W2903277833","https://openalex.org/W2997591727","https://openalex.org/W4252095012","https://openalex.org/W4300529352"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W1527532029","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2772323916","https://openalex.org/W2281307425","https://openalex.org/W1511346092","https://openalex.org/W2464405057"],"abstract_inverted_index":{"In":[0,65],"this":[1,155],"paper,":[2],"we":[3,73,142],"investigate":[4],"the":[5,76,84,116,122,130,169,177],"state-of-the-art":[6],"of":[7,15,68,90,105,124,139,179,184],"machine":[8,70],"learning":[9,71],"models":[10,32],"to":[11,58,92,126,153],"infer":[12],"sociodemographic":[13,35],"attributes":[14,109],"Wikipedia":[16,140,149,185],"editors":[17],"based":[18],"on":[19,129,148],"their":[20],"public":[21],"profile":[22,51,63,182],"pages":[23,183],"and":[24,96,114,150,172],"corresponding":[25],"implications":[26],"for":[27,33,83,94],"editor":[28,50,146],"privacy.":[29],"To":[30],"build":[31],"inferring":[34],"attributes,":[36],"ground":[37],"truth":[38],"labels":[39],"are":[40,56],"obtained":[41,82],"via":[42],"different":[43,69],"strategies,":[44],"using":[45,135],"publicly":[46,136],"disclosed":[47,137],"information":[48,138],"from":[49,61],"pages.":[52],"Different":[53],"embedding":[54],"techniques":[55],"used":[57],"derive":[59],"features":[60],"editors\u2019":[62],"texts.":[64],"comparative":[66],"evaluations":[67],"models,":[72],"show":[74],"that":[75,174],"highest":[77],"prediction":[78],"accuracy":[79],"can":[80,161],"be":[81],"attribute":[85],"gender,":[86],"with":[87,176],"precision":[88],"values":[89],"82%":[91],"91%":[93],"women":[95],"men":[97],"respectively,":[98],"as":[99,101],"well":[100],"an":[102],"averaged":[103],"F1-score":[104],"0.78.":[106],"For":[107],"other":[108],"like":[110],"age":[111],"group,":[112],"education,":[113],"religion,":[115],"utilized":[117],"classifiers":[118],"exhibit":[119],"F1-scores":[120],"in":[121],"range":[123],"0.32":[125],"0.74,":[127],"depending":[128],"model":[131],"class.":[132],"By":[133],"merely":[134],"editors,":[141],"highlight":[143],"issues":[144],"surrounding":[145],"privacy":[147],"discuss":[151],"ways":[152],"mitigate":[154],"problem.":[156],"We":[157],"believe":[158],"our":[159],"work":[160],"help":[162],"start":[163],"a":[164],"conversation":[165],"about":[166],"carefully":[167],"weighing":[168],"potential":[170],"benefits":[171],"harms":[173],"come":[175],"existence":[178],"information-rich,":[180],"pre-labeled":[181],"editors.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
