{"id":"https://openalex.org/W4387579388","doi":"https://doi.org/10.1145/3625679","title":"Hate Speech Detection in Limited Data Contexts Using Synthetic Data Generation","display_name":"Hate Speech Detection in Limited Data Contexts Using Synthetic Data Generation","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387579388","doi":"https://doi.org/10.1145/3625679"},"language":"en","primary_location":{"id":"doi:10.1145/3625679","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625679","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625679","source":{"id":"https://openalex.org/S4387291547","display_name":"ACM Journal on Computing and Sustainable Societies","issn_l":"2834-5533","issn":["2834-5533"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal on Computing and Sustainable Societies","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3625679","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009243074","display_name":"Aman Khullar","orcid":"https://orcid.org/0000-0003-4670-6407"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aman Khullar","raw_affiliation_strings":["Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050948555","display_name":"Daniel Nkemelu","orcid":"https://orcid.org/0000-0001-9394-004X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Nkemelu","raw_affiliation_strings":["Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101896049","display_name":"Viet Cuong Nguyen","orcid":"https://orcid.org/0000-0002-8504-9350"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Cuong Nguyen","raw_affiliation_strings":["Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026238738","display_name":"Michael L. Best","orcid":"https://orcid.org/0000-0001-8156-9001"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Best","raw_affiliation_strings":["Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009243074"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.7397,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87812502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":1.0,"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":1.0,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9526000022888184,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9277999997138977,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7509592771530151},{"id":"https://openalex.org/keywords/offensive","display_name":"Offensive","score":0.7012453675270081},{"id":"https://openalex.org/keywords/disclaimer","display_name":"Disclaimer","score":0.6246086359024048},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5659932494163513},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4997861385345459},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4293716549873352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4267506003379822},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4260956048965454},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4214381277561188},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.41178521513938904},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4090054929256439},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23561164736747742},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15697890520095825},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13826096057891846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509592771530151},{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.7012453675270081},{"id":"https://openalex.org/C2777080597","wikidata":"https://www.wikidata.org/wiki/Q906118","display_name":"Disclaimer","level":2,"score":0.6246086359024048},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5659932494163513},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4997861385345459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4293716549873352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4267506003379822},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4260956048965454},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4214381277561188},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.41178521513938904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4090054929256439},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23561164736747742},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15697890520095825},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13826096057891846},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625679","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625679","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625679","source":{"id":"https://openalex.org/S4387291547","display_name":"ACM Journal on Computing and Sustainable Societies","issn_l":"2834-5533","issn":["2834-5533"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal on Computing and Sustainable Societies","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3625679","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625679","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625679","source":{"id":"https://openalex.org/S4387291547","display_name":"ACM Journal on Computing and Sustainable Societies","issn_l":"2834-5533","issn":["2834-5533"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal on Computing and Sustainable Societies","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308555","display_name":"Carter Center","ror":"https://ror.org/030mbxz29"},{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387579388.pdf","grobid_xml":"https://content.openalex.org/works/W4387579388.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W2595653137","https://openalex.org/W2618851150","https://openalex.org/W2805807672","https://openalex.org/W2887782043","https://openalex.org/W2889016530","https://openalex.org/W2951476960","https://openalex.org/W2954566102","https://openalex.org/W2954996726","https://openalex.org/W2956090150","https://openalex.org/W2962862931","https://openalex.org/W2964243274","https://openalex.org/W2971150411","https://openalex.org/W2983342160","https://openalex.org/W3010360545","https://openalex.org/W3033226103","https://openalex.org/W3035032094","https://openalex.org/W3035390927","https://openalex.org/W3038047279","https://openalex.org/W3094450620","https://openalex.org/W3096831136","https://openalex.org/W3100198908","https://openalex.org/W3101574506","https://openalex.org/W3104182623","https://openalex.org/W3104209339","https://openalex.org/W3111436990","https://openalex.org/W3116813032","https://openalex.org/W3118142489","https://openalex.org/W3130315320","https://openalex.org/W3130335560","https://openalex.org/W3136590789","https://openalex.org/W3160042174","https://openalex.org/W3163839574","https://openalex.org/W3172559340","https://openalex.org/W3173380736","https://openalex.org/W3183778618","https://openalex.org/W3198836239","https://openalex.org/W3208049241","https://openalex.org/W3212112365","https://openalex.org/W4213259260","https://openalex.org/W4214646284","https://openalex.org/W4280576095","https://openalex.org/W4283155872","https://openalex.org/W4285210452","https://openalex.org/W4292779060","https://openalex.org/W4312750750","https://openalex.org/W4372215781","https://openalex.org/W4392637264","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2908791978","https://openalex.org/W3189604486","https://openalex.org/W2622971530","https://openalex.org/W4252575750","https://openalex.org/W4254557320","https://openalex.org/W1564737387","https://openalex.org/W2608579074","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"A":[0],"growing":[1],"body":[2],"of":[3,16,31,55,81,83,102,121,210,253],"work":[4,222,236],"has":[5,23],"focused":[6],"on":[7,167,182],"text":[8],"classification":[9,154],"methods":[10,116],"for":[11,85,151,226],"detecting":[12],"the":[13,79,131,135,140,183,187,208,251,254],"increasing":[14],"amount":[15],"hate":[17,87,103,122,132,141,152,197,232],"speech":[18,88,104,123,153,198],"posted":[19],"online.":[20],"This":[21,48,190,235],"progress":[22],"been":[24],"limited":[25,45,91,204],"to":[26,38,61,117,147,195,217,231,250],"only":[27,181],"a":[28,53,73,100,107,126,164,178],"select":[29],"number":[30],"highly":[32],"resourced":[33],"languages":[34],"causing":[35],"detection":[36,89,199],"systems":[37],"either":[39],"under-perform":[40],"or":[41],"not":[42],"exist":[43],"in":[44,65,90,106,125,134,156,174,186,203],"data":[46,74,84,92,96,124,150,169,205],"contexts.":[47,206],"is":[49],"mostly":[50],"caused":[51],"by":[52],"lack":[54,82],"training":[56,149],"data,":[57],"which":[58],"are":[59,240],"expensive":[60],"collect":[62],"and":[63,158,173,229,242],"curate":[64],"these":[66,214],"settings.":[67],"In":[68],"this":[69,221],"work,":[70],"we":[71,113],"propose":[72],"augmentation":[75],"approach":[76,146],"that":[77,129,163,239],"addresses":[78],"problem":[80],"online":[86],"contexts":[93,215],"using":[94],"synthetic":[95,168],"generation":[97],"techniques.":[98],"Given":[99],"handful":[101],"examples":[105,120,137],"high-resource":[108],"language":[109,128],"such":[110],"as":[111],"English,":[112],"present":[114],"three":[115],"synthesize":[118],"new":[119],"target":[127,188],"retains":[130],"sentiment":[133],"original":[136],"but":[138],"transfers":[139],"targets.":[142],"We":[143],"apply":[144],"our":[145,224],"generate":[148],"tasks":[155],"Hindi":[157],"Vietnamese.":[159],"Our":[160],"findings":[161],"show":[162],"model":[165,179],"trained":[166,180],"performs":[170],"comparably":[171],"to,":[172],"some":[175],"cases":[176],"outperforms,":[177],"samples":[184],"available":[185],"domain.":[189],"method":[191],"can":[192],"be":[193,247],"adopted":[194],"bootstrap":[196],"models":[200],"from":[201],"scratch":[202],"As":[207],"growth":[209],"social":[211],"media":[212],"within":[213],"continues":[216],"outstrip":[218],"response":[219,230],"efforts,":[220],"furthers":[223],"capacities":[225],"detection,":[227],"understanding,":[228],"speech.":[233],"Disclaimer:":[234],"contains":[237],"terms":[238],"offensive":[241],"hateful.":[243],"These,":[244],"however,":[245],"cannot":[246],"avoided":[248],"due":[249],"nature":[252],"work.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
