{"id":"https://openalex.org/W3001219191","doi":"https://doi.org/10.1109/octa49274.2020.9151853","title":"BERT and fastText Embeddings for Automatic Detection of Toxic Speech","display_name":"BERT and fastText Embeddings for Automatic Detection of Toxic Speech","publication_year":2020,"publication_date":"2020-02-01","ids":{"openalex":"https://openalex.org/W3001219191","doi":"https://doi.org/10.1109/octa49274.2020.9151853","mag":"3001219191"},"language":"en","primary_location":{"id":"doi:10.1109/octa49274.2020.9151853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/octa49274.2020.9151853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Multi-Conference on: \u201cOrganization of Knowledge and Advanced Technologies\u201d (OCTA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.inria.fr/hal-02448197","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051909338","display_name":"Ashwin Geet d'Sa","orcid":"https://orcid.org/0000-0002-0212-1370"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ashwin Geet D'Sa","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073463405","display_name":"Irina Illina","orcid":"https://orcid.org/0000-0003-2598-4643"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Irina Illina","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046546502","display_name":"Dominique Fohr","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dominique Fohr","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.583,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.97793644,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998999834060669,"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":0.9998999834060669,"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/offensive","display_name":"Offensive","score":0.8633530139923096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.77384352684021},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5646077394485474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5394225120544434},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5378576517105103},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5370463728904724},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.533348560333252},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5084006190299988},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5069029927253723},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48244839906692505},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4376176595687866},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4224246144294739},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2533407211303711},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22686725854873657},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.19568350911140442}],"concepts":[{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.8633530139923096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77384352684021},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5646077394485474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5394225120544434},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5378576517105103},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5370463728904724},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.533348560333252},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5084006190299988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5069029927253723},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48244839906692505},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4376176595687866},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4224246144294739},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2533407211303711},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22686725854873657},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.19568350911140442},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/octa49274.2020.9151853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/octa49274.2020.9151853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Multi-Conference on: \u201cOrganization of Knowledge and Advanced Technologies\u201d (OCTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02448197v1","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02448197","pdf_url":null,"source":{"id":"https://openalex.org/S4406922276","display_name":"INRIA a CCSD electronic archive server","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIIE 2020 - Information Systems and Economic Intelligence","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-02448197v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02448197","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIIE 2020 - Information Systems and Economic Intelligence; International Multi-Conference on:\u201cOrganization of Knowledge and Advanced Technologies\u201d(OCTA), Feb 2020, Tunis, Tunisia","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02448197v1","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02448197","pdf_url":null,"source":{"id":"https://openalex.org/S4406922276","display_name":"INRIA a CCSD electronic archive server","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIIE 2020 - Information Systems and Economic Intelligence","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W2157331557","https://openalex.org/W2250539671","https://openalex.org/W2340954483","https://openalex.org/W2493916176","https://openalex.org/W2595653137","https://openalex.org/W2613977835","https://openalex.org/W2803765190","https://openalex.org/W2953646920","https://openalex.org/W2954352578","https://openalex.org/W2955556640","https://openalex.org/W2956043463","https://openalex.org/W2963943967","https://openalex.org/W2973034686","https://openalex.org/W3103061166","https://openalex.org/W6614078139","https://openalex.org/W6739901393","https://openalex.org/W6745633177","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W1568520348","https://openalex.org/W3214407891","https://openalex.org/W3194113117","https://openalex.org/W3213194066","https://openalex.org/W4287020359","https://openalex.org/W268355439","https://openalex.org/W4382934300","https://openalex.org/W2121061354","https://openalex.org/W4285388059","https://openalex.org/W3172030588"],"abstract_inverted_index":{"With":[0],"the":[1,8,24,53,79,92,108,174],"expansion":[2],"of":[3,10,14,26,39,42,55,131,137,163,195],"Internet":[4],"usage,":[5],"catering":[6],"to":[7,50,114],"dissemination":[9],"thoughts":[11],"and":[12,68,84,117,139,145,152,166],"expressions":[13],"an":[15,20],"individual,":[16],"there":[17,73],"has":[18],"been":[19],"immense":[21],"increase":[22],"in":[23,87,161],"spread":[25],"online":[27,43,102,122],"hate":[28,83],"speech.":[29,98],"Social":[30],"media,":[31],"community":[32],"forums,":[33],"discussion":[34],"platforms":[35],"are":[36,47],"few":[37],"examples":[38],"common":[40],"playground":[41],"discussions":[44],"where":[45],"people":[46,62],"freely":[48],"allowed":[49],"communicate.":[51],"However,":[52],"freedom":[54],"speech":[56,104,120,133],"may":[57],"be":[58,189],"misused":[59],"by":[60,63,107],"some":[61],"arguing":[64],"aggressively,":[65],"offending":[66],"others":[67],"spreading":[69],"verbal":[70],"violence.":[71],"As":[72],"is":[74,105,112],"no":[75],"clear":[76],"distinction":[77],"between":[78],"terms":[80,95],"offensive,":[81],"abusive,":[82],"toxic":[85,97,103,119,132],"speech,":[86],"this":[88,125],"paper":[89],"we":[90,127],"consider":[91],"above":[93],"mentioned":[94],"as":[96],"In":[99],"many":[100],"countries,":[101],"punishable":[106],"law.":[109],"Thus,":[110],"it":[111],"important":[113],"automatically":[115],"detect":[116],"remove":[118],"from":[121],"medias.":[123],"Through":[124],"work,":[126],"propose":[128],"automatic":[129],"classification":[130,147],"using":[134,148,168],"embedding":[135],"representations":[136],"words":[138],"deep-learning":[140],"techniques.":[141],"We":[142,178],"perform":[143],"binary":[144],"multi-class":[146],"a":[149,157,169],"Twitter":[150],"corpus":[151],"study":[153],"two":[154],"approaches:":[155],"(a)":[156],"method":[158],"which":[159],"consists":[160],"extracting":[162],"word":[164],"embeddings":[165],"then":[167],"DNN":[170],"classifier;":[171],"(b)":[172],"fine-tuning":[173,182],"pre-trained":[175],"BERT":[176,181],"model.":[177],"observed":[179],"that":[180],"performed":[183],"much":[184],"better.":[185],"Proposed":[186],"methodology":[187],"can":[188],"used":[190],"for":[191],"any":[192],"other":[193],"type":[194],"social":[196],"media":[197],"comments.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
