{"id":"https://openalex.org/W4385567962","doi":"https://doi.org/10.1145/3580305.3599823","title":"Fair Multilingual Vandalism Detection System for Wikipedia","display_name":"Fair Multilingual Vandalism Detection System for Wikipedia","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385567962","doi":"https://doi.org/10.1145/3580305.3599823"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599823","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3580305.3599823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005178641","display_name":"Mykola Trokhymovych","orcid":"https://orcid.org/0000-0001-9932-7094"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Mykola Trokhymovych","raw_affiliation_strings":["Pompeu Fabra University, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0001-9932-7094","affiliations":[{"raw_affiliation_string":"Pompeu Fabra University, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101496219","display_name":"Muniza Aslam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126245","display_name":"Wikimedia Foundation","ror":"https://ror.org/032q98j12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210126245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muniza Aslam","raw_affiliation_strings":["Wikimedia Foundation, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0009-0005-9171-060X","affiliations":[{"raw_affiliation_string":"Wikimedia Foundation, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210126245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018298207","display_name":"Ai-Jou Chou","orcid":"https://orcid.org/0000-0002-5269-7167"},"institutions":[{"id":"https://openalex.org/I4210126245","display_name":"Wikimedia Foundation","ror":"https://ror.org/032q98j12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210126245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ai-Jou Chou","raw_affiliation_strings":["Wikimedia Foundation, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5269-7167","affiliations":[{"raw_affiliation_string":"Wikimedia Foundation, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210126245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076204770","display_name":"Ricardo Baeza\u2010Yates","orcid":"https://orcid.org/0000-0003-3208-9778"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I4210148712","display_name":"Silicon Valley University","ror":"https://ror.org/04jk6hn97","country_code":"US","type":"education","lineage":["https://openalex.org/I4210148712"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricardo Baeza-Yates","raw_affiliation_strings":["EAI, Northeastern University, Silicon Valley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3208-9778","affiliations":[{"raw_affiliation_string":"EAI, Northeastern University, Silicon Valley, CA, USA","institution_ids":["https://openalex.org/I4210148712","https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042104049","display_name":"Diego S\u00e1ez-Trumper","orcid":"https://orcid.org/0000-0002-7679-5423"},"institutions":[{"id":"https://openalex.org/I4210126245","display_name":"Wikimedia Foundation","ror":"https://ror.org/032q98j12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210126245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Saez-Trumper","raw_affiliation_strings":["Wikimedia Foundation, San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7679-5423","affiliations":[{"raw_affiliation_string":"Wikimedia Foundation, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210126245"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005178641"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15547961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4981","last_page":"4990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9997000098228455,"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":0.9997000098228455,"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/T13157","display_name":"Cancer-related gene regulation","score":0.9882000088691711,"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"}},{"id":"https://openalex.org/T12534","display_name":"Protein Degradation and Inhibitors","score":0.9553999900817871,"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/patrolling","display_name":"Patrolling","score":0.8795312643051147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811151385307312},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5467352867126465},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5392590165138245},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.526129961013794},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3810470402240753},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37004441022872925},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3617744445800781},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35677269101142883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3454661965370178},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.19252067804336548},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08099669218063354}],"concepts":[{"id":"https://openalex.org/C110698143","wikidata":"https://www.wikidata.org/wiki/Q651389","display_name":"Patrolling","level":2,"score":0.8795312643051147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811151385307312},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5467352867126465},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5392590165138245},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.526129961013794},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3810470402240753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37004441022872925},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3617744445800781},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35677269101142883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3454661965370178},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.19252067804336548},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08099669218063354},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599823","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3580305.3599823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G300979063","display_name":null,"funder_award_id":"10.13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G4115436907","display_name":null,"funder_award_id":"MCIN/AEI /10.13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5080475149","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6717538712","display_name":null,"funder_award_id":"AEI /10.13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7266728691","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G992696456","display_name":null,"funder_award_id":"CEX2021-001195-M","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2036291768","https://openalex.org/W2063185719","https://openalex.org/W2120845601","https://openalex.org/W2146314642","https://openalex.org/W2282821441","https://openalex.org/W2537475616","https://openalex.org/W2903277833","https://openalex.org/W2912083425","https://openalex.org/W2942080774","https://openalex.org/W2963341956","https://openalex.org/W2998862821","https://openalex.org/W3012915092","https://openalex.org/W3085747564","https://openalex.org/W3094328607","https://openalex.org/W3105435131"],"related_works":["https://openalex.org/W170273588","https://openalex.org/W2337788814","https://openalex.org/W2092973197","https://openalex.org/W2750075801","https://openalex.org/W3164948662","https://openalex.org/W4400413234","https://openalex.org/W3153597579","https://openalex.org/W4385336128","https://openalex.org/W4394398790","https://openalex.org/W4399455186"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,26,77,92],"novel":[4],"design":[5],"of":[6,29,55,83,95,119],"the":[7,12,19,47,56,63,81,104],"system":[8,57],"aimed":[9],"at":[10],"supporting":[11],"Wikipedia":[13,87],"community":[14],"in":[15,66,68,76,80],"addressing":[16],"vandalism":[17],"on":[18],"platform.":[20],"To":[21],"achieve":[22],"this,":[23],"we":[24],"collected":[25],"massive":[27],"dataset":[28,49],"47":[30],"languages,":[31],"and":[32,36],"applied":[33],"advanced":[34],"filtering":[35],"feature":[37],"engineering":[38],"techniques,":[39],"including":[40],"multilingual":[41],"masked":[42],"language":[43],"modeling":[44],"to":[45,91],"build":[46],"training":[48],"from":[50],"human-generated":[51],"data.":[52],"The":[53],"performance":[54],"was":[58],"evaluated":[59],"through":[60],"comparison":[61],"with":[62],"one":[64],"used":[65],"production":[67],"Wikipedia,":[69],"known":[70],"as":[71],"ORES.":[72],"Our":[73],"research":[74],"results":[75,105],"significant":[78],"increase":[79],"number":[82],"languages":[84],"covered,":[85],"making":[86],"patrolling":[88],"more":[89,110],"efficient":[90],"wider":[93],"range":[94],"communities.":[96],"Furthermore,":[97],"our":[98],"model":[99],"outperforms":[100],"ORES,":[101],"ensuring":[102],"that":[103],"provided":[106],"are":[107],"not":[108],"only":[109],"accurate":[111],"but":[112],"also":[113],"less":[114],"biased":[115],"against":[116],"certain":[117],"groups":[118],"contributors.":[120]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}