{"id":"https://openalex.org/W4399629521","doi":"https://doi.org/10.1145/3630744.3663609","title":"Sexism Detection on a Data Diet","display_name":"Sexism Detection on a Data Diet","publication_year":2024,"publication_date":"2024-05-21","ids":{"openalex":"https://openalex.org/W4399629521","doi":"https://doi.org/10.1145/3630744.3663609"},"language":"en","primary_location":{"id":"doi:10.1145/3630744.3663609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630744.3663609","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630744.3663609","source":null,"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 16th ACM Web Science Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630744.3663609","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099082840","display_name":"Rabiraj Bandyopadhyay","orcid":"https://orcid.org/0009-0000-5036-015X"},"institutions":[{"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":true,"raw_author_name":"Rabiraj Bandyopadhyay","raw_affiliation_strings":["GESIS Leibniz Institute for the Social Sciences, Germany"],"affiliations":[{"raw_affiliation_string":"GESIS Leibniz Institute for the Social Sciences, Germany","institution_ids":["https://openalex.org/I4210101898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067592463","display_name":"Dennis Assenmacher","orcid":"https://orcid.org/0000-0001-9219-1956"},"institutions":[{"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":"Dennis Assenmacher","raw_affiliation_strings":["GESIS Leibniz Institute for the Social Sciences, Germany"],"affiliations":[{"raw_affiliation_string":"GESIS Leibniz Institute for the Social Sciences, Germany","institution_ids":["https://openalex.org/I4210101898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056892202","display_name":"Jos\u00e9 M. Alonso","orcid":"https://orcid.org/0000-0003-3673-421X"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]},{"id":"https://openalex.org/I4210111807","display_name":"Center for Research in Molecular Medicine and Chronic Diseases","ror":"https://ror.org/0280bnq76","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210111807"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose M. Alonso-Moral","raw_affiliation_strings":["Centro Singular de Investigaci\u00f3n en Tecnolox\u00edas Intelixentes (CiTIUS), Spain and Universidade de Santiago de Compostela, Spain"],"affiliations":[{"raw_affiliation_string":"Centro Singular de Investigaci\u00f3n en Tecnolox\u00edas Intelixentes (CiTIUS), Spain and Universidade de Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I4210111807","https://openalex.org/I200284239"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044130443","display_name":"Claudia Wagner","orcid":"https://orcid.org/0000-0002-0640-8221"},"institutions":[{"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"]},{"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":"Claudia Wagner","raw_affiliation_strings":["GESIS Leibniz Institute for the Social Sciences, Germany and RWTH Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"GESIS Leibniz Institute for the Social Sciences, Germany and RWTH Aachen, Germany","institution_ids":["https://openalex.org/I4210101898","https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5099082840"],"corresponding_institution_ids":["https://openalex.org/I4210101898"],"apc_list":null,"apc_paid":null,"fwci":0.695,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73926996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.7704290151596069},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7399883270263672},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7099834680557251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6476215124130249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6427717208862305},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6154558062553406},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5696579217910767},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5632768273353577},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48496532440185547},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.47655728459358215},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42764273285865784},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4186934232711792},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4051131308078766},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1100861132144928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704290151596069},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7399883270263672},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7099834680557251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6476215124130249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6427717208862305},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6154558062553406},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5696579217910767},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5632768273353577},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48496532440185547},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.47655728459358215},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42764273285865784},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4186934232711792},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4051131308078766},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1100861132144928},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630744.3663609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630744.3663609","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630744.3663609","source":null,"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 16th ACM Web Science Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3630744.3663609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630744.3663609","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630744.3663609","source":null,"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 16th ACM Web Science Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399629521.pdf"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1840435438","https://openalex.org/W2108598243","https://openalex.org/W3080532707","https://openalex.org/W3170644058","https://openalex.org/W4210306310","https://openalex.org/W4386424123"],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361","https://openalex.org/W4285322112","https://openalex.org/W4292794239"],"abstract_inverted_index":{"There":[0],"is":[1,23,52],"an":[2],"increase":[3],"in":[4,14,28,43,149,178,204],"the":[5,12,15,29,78,85,91,107,124,131,171,188,196,205,212],"proliferation":[6],"of":[7,17,31,63,68,77,109,126,157,190,211],"online":[8],"hate":[9],"commensurate":[10],"with":[11,138,151],"rise":[13],"usage":[16],"social":[18],"media.":[19],"In":[20,94],"response,":[21],"there":[22],"also":[24,168],"a":[25,60,110,115,119,154,208],"significant":[26,163],"advancement":[27],"creation":[30],"automated":[32],"tools":[33],"aimed":[34],"at":[35],"identifying":[36],"harmful":[37,191],"text":[38],"content":[39,192],"using":[40],"approaches":[41],"grounded":[42],"Natural":[44,179],"Language":[45,180],"Processing":[46],"and":[47,117,146,193],"Deep":[48,56],"Learning.":[49],"Although":[50],"it":[51],"known":[53],"that":[54,71,87,148,170],"training":[55,114],"Learning":[57],"models":[58,72],"require":[59],"substantial":[61],"amount":[62],"annotated":[64],"data,":[65,175],"recent":[66],"line":[67],"work":[69,153],"suggests":[70],"trained":[73,89,134],"on":[74,90,135,142],"specific":[75],"subsets":[76],"data":[79,111,136],"still":[80],"retain":[81],"performance":[82,133,164],"comparable":[83],"to":[84,105,123,187,207],"model":[86,116,132],"was":[88],"full":[92],"dataset.":[93],"this":[95],"work,":[96],"we":[97,100,167],"show":[98],"how":[99],"can":[101,159],"leverage":[102],"influence":[103],"scores":[104],"estimate":[106],"importance":[108],"point":[112],"while":[113],"designing":[118],"pruning":[120,140,174],"strategy":[121],"applied":[122],"case":[125],"sexism":[127],"detection.":[128],"We":[129],"evaluate":[130],"pruned":[137],"different":[139],"strategies":[141,172],"three":[143],"out-of-domain":[144],"datasets":[145],"find,":[147],"accordance":[150],"other":[152],"large":[155],"fraction":[156],"instances":[158],"be":[160],"removed":[161],"without":[162],"drop.":[165],"However,":[166],"discover":[169],"for":[173],"previously":[176],"successful":[177],"Inference":[181],"tasks,":[182],"do":[183],"not":[184],"readily":[185],"apply":[186],"detection":[189],"instead":[194],"amplify":[195],"already":[197],"prevalent":[198],"class":[199],"imbalance":[200],"even":[201],"more,":[202],"leading":[203],"worst-case":[206],"complete":[209],"absence":[210],"hateful":[213],"class.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}