{"id":"https://openalex.org/W4411435552","doi":"https://doi.org/10.3390/computers14060239","title":"UA-HSD-2025: Multi-Lingual Hate Speech Detection from Tweets Using Pre-Trained Transformers","display_name":"UA-HSD-2025: Multi-Lingual Hate Speech Detection from Tweets Using Pre-Trained Transformers","publication_year":2025,"publication_date":"2025-06-18","ids":{"openalex":"https://openalex.org/W4411435552","doi":"https://doi.org/10.3390/computers14060239"},"language":"en","primary_location":{"id":"doi:10.3390/computers14060239","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14060239","pdf_url":"https://www.mdpi.com/2073-431X/14/6/239/pdf?version=1750253721","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/14/6/239/pdf?version=1750253721","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110017583","display_name":"Muhammad Ahmad","orcid":"https://orcid.org/0009-0003-8799-8212"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Muhammad Ahmad","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional (CIC-PN), Mexico City 07738, Mexico"],"raw_orcid":"https://orcid.org/0009-0003-8799-8212","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional (CIC-PN), Mexico City 07738, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095866305","display_name":"Muhammad Waqas","orcid":"https://orcid.org/0000-0003-2534-6916"},"institutions":[{"id":"https://openalex.org/I174731842","display_name":"Islamia University of Bahawalpur","ror":"https://ror.org/002rc4w13","country_code":"PK","type":"education","lineage":["https://openalex.org/I174731842"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Waqas","raw_affiliation_strings":["Department of Software Engineering, The Islamia University of Bahawalpur, Bahawalpur 63100, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, The Islamia University of Bahawalpur, Bahawalpur 63100, Pakistan","institution_ids":["https://openalex.org/I174731842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083593624","display_name":"Ameer Hamza","orcid":"https://orcid.org/0000-0001-6158-4861"},"institutions":[{"id":"https://openalex.org/I174731842","display_name":"Islamia University of Bahawalpur","ror":"https://ror.org/002rc4w13","country_code":"PK","type":"education","lineage":["https://openalex.org/I174731842"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ameer Hamza","raw_affiliation_strings":["Department of Software Engineering, The Islamia University of Bahawalpur, Bahawalpur 63100, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, The Islamia University of Bahawalpur, Bahawalpur 63100, Pakistan","institution_ids":["https://openalex.org/I174731842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036614024","display_name":"Sardar Usman","orcid":"https://orcid.org/0000-0003-4698-6461"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sardar Usman","raw_affiliation_strings":["School of Informatics and Robotics, Institute of Arts and Culture, Lahore 54000, Pakistan"],"raw_orcid":"https://orcid.org/0000-0003-4698-6461","affiliations":[{"raw_affiliation_string":"School of Informatics and Robotics, Institute of Arts and Culture, Lahore 54000, Pakistan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010915932","display_name":"Ildar Batyrshin","orcid":"https://orcid.org/0000-0003-0241-7902"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ildar Batyrshin","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional (CIC-PN), Mexico City 07738, Mexico"],"raw_orcid":"https://orcid.org/0000-0003-0241-7902","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional (CIC-PN), Mexico City 07738, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008287867","display_name":"Grigori Sidorov","orcid":"https://orcid.org/0000-0003-3901-3522"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Grigori Sidorov","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional (CIC-PN), Mexico City 07738, Mexico"],"raw_orcid":"https://orcid.org/0000-0003-3901-3522","affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional (CIC-PN), Mexico City 07738, Mexico","institution_ids":["https://openalex.org/I59361560"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008287867"],"corresponding_institution_ids":["https://openalex.org/I59361560"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":11.4343,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98138133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"14","issue":"6","first_page":"239","last_page":"239"},"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"}},{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9362000226974487,"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":0.8219766616821289},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6843390464782715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6719918847084045},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5023062229156494},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4855741858482361},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4479838013648987},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.44150227308273315},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.42576563358306885},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.42348480224609375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3527466058731079},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.18189868330955505},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1651705503463745},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12407994270324707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219766616821289},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6843390464782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6719918847084045},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5023062229156494},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4855741858482361},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4479838013648987},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.44150227308273315},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.42576563358306885},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.42348480224609375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3527466058731079},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.18189868330955505},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1651705503463745},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12407994270324707},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers14060239","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14060239","pdf_url":"https://www.mdpi.com/2073-431X/14/6/239/pdf?version=1750253721","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:87c260129dc54121837f97c8c7837b70","is_oa":true,"landing_page_url":"https://doaj.org/article/87c260129dc54121837f97c8c7837b70","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 14, Iss 6, p 239 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers14060239","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14060239","pdf_url":"https://www.mdpi.com/2073-431X/14/6/239/pdf?version=1750253721","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411435552.pdf","grobid_xml":"https://content.openalex.org/works/W4411435552.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2022077643","https://openalex.org/W2610373898","https://openalex.org/W2897464817","https://openalex.org/W3010559454","https://openalex.org/W3126184898","https://openalex.org/W3172414534","https://openalex.org/W3179199540","https://openalex.org/W3212567067","https://openalex.org/W3213226375","https://openalex.org/W4205602376","https://openalex.org/W4280576095","https://openalex.org/W4283454882","https://openalex.org/W4294685900","https://openalex.org/W4384520880","https://openalex.org/W4388524030","https://openalex.org/W4395071539","https://openalex.org/W4395096466","https://openalex.org/W4399199169","https://openalex.org/W4400315109","https://openalex.org/W4400721756","https://openalex.org/W4402075294","https://openalex.org/W4402076569","https://openalex.org/W4402265072","https://openalex.org/W4403431661","https://openalex.org/W4403638781","https://openalex.org/W4404111206","https://openalex.org/W4404649207","https://openalex.org/W4404782224","https://openalex.org/W4405709788","https://openalex.org/W4406172215","https://openalex.org/W4406228183","https://openalex.org/W4406444864","https://openalex.org/W4406657382","https://openalex.org/W4408471868","https://openalex.org/W4410398257","https://openalex.org/W6843283995","https://openalex.org/W6873480773"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W4382934300","https://openalex.org/W2121061354","https://openalex.org/W4285388059"],"abstract_inverted_index":{"The":[0,128],"rise":[1],"in":[2,224,239],"social":[3],"media":[4],"has":[5],"improved":[6],"communication":[7],"but":[8],"also":[9],"amplified":[10],"the":[11,42,86,117,147,207,210],"spread":[12],"of":[13,46,92,119,209],"hate":[14,50,93,107],"speech,":[15],"creating":[16],"serious":[17],"societal":[18],"risks.":[19],"Automated":[20],"detection":[21],"remains":[22],"difficult":[23],"due":[24],"to":[25,101,115,156,163],"subjectivity,":[26],"linguistic":[27],"diversity,":[28],"and":[29,48,77,105,125,195,197,230,233,236,245],"implicit":[30],"language.":[31],"While":[32],"prior":[33],"research":[34],"focuses":[35],"on":[36,206],"high-resource":[37],"languages,":[38],"this":[39,58,60],"study":[40,61],"addresses":[41],"underexplored":[43],"multilingual":[44,120,124,149],"challenges":[45,118],"Arabic":[47],"Urdu":[49,246],"speech":[51,108],"through":[52],"a":[53,71,103,122,137,143,152],"comprehensive":[54],"approach.":[55,127],"To":[56],"achieve":[57],"objective,":[59],"makes":[62],"four":[63],"different":[64,167,177,180],"key":[65],"contributions.":[66],"First,":[67],"we":[68,96,111,172],"have":[69,173],"created":[70,97],"unique":[72],"multi-lingual,":[73],"manually":[74],"annotated":[75],"binary":[76,225],"multi-class":[78,90,240],"dataset":[79],"(UA-HSD-2025)":[80],"sourced":[81],"from":[82],"X,":[83],"which":[84],"contains":[85],"five":[87],"most":[88],"important":[89],"categories":[91],"speech.":[94],"Secondly,":[95],"detailed":[98],"annotation":[99],"guidelines":[100],"make":[102],"robust":[104],"perfect":[106],"dataset.":[109],"Third,":[110],"explore":[112],"two":[113],"strategies":[114],"address":[116],"data:":[121],"joint":[123,148],"translation-based":[126,129],"approach":[130,150],"involves":[131],"converting":[132],"all":[133],"input":[134],"text":[135,165],"into":[136],"single":[138],"target":[139],"language":[140],"before":[141],"applying":[142],"classifier.":[144],"In":[145],"contrast,":[146],"employs":[151],"unified":[153],"model":[154,214],"trained":[155],"handle":[157],"multiple":[158],"languages":[159,168],"simultaneously,":[160],"enabling":[161],"it":[162],"classify":[164],"across":[166],"without":[169],"translation.":[170],"Finally,":[171],"employed":[174],"state-of-the-art":[175],"54":[176],"experiments":[178],"using":[179,183,187,201],"machine":[181],"learning":[182,186,219],"TF-IDF,":[184],"deep":[185],"advanced":[188,202],"pre-trained":[189,198],"word":[190],"embeddings":[191],"such":[192],"as":[193],"FastText":[194],"Glove,":[196],"language-based":[199,213],"models":[200],"contextual":[203],"embeddings.":[204],"Based":[205],"analysis":[208],"results,":[211],"our":[212],"(XLM-R)":[215],"outperformed":[216],"traditional":[217],"supervised":[218],"approaches,":[220],"achieving":[221],"0.99":[222],"accuracy":[223,238],"classification":[226,241],"for":[227,242],"Arabic,":[228,244],"Urdu,":[229],"joint-multilingual":[231],"datasets,":[232,247],"0.95,":[234],"0.94,":[235],"0.94":[237],"joint-multilingual,":[243],"respectively.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
