{"id":"https://openalex.org/W4385723172","doi":"https://doi.org/10.1017/s1351324923000402","title":"Emojis as anchors to detect Arabic offensive language and hate speech","display_name":"Emojis as anchors to detect Arabic offensive language and hate speech","publication_year":2023,"publication_date":"2023-08-10","ids":{"openalex":"https://openalex.org/W4385723172","doi":"https://doi.org/10.1017/s1351324923000402"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324923000402","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000402","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/2C1DFD708D4EE24B4E22C5664BD9B2E1/S1351324923000402a.pdf/div-class-title-emojis-as-anchors-to-detect-arabic-offensive-language-and-hate-speech-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/2C1DFD708D4EE24B4E22C5664BD9B2E1/S1351324923000402a.pdf/div-class-title-emojis-as-anchors-to-detect-arabic-offensive-language-and-hate-speech-div.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102924560","display_name":"Hamdy Mubarak","orcid":"https://orcid.org/0000-0002-9051-6240"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Hamdy Mubarak","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049532042","display_name":"Sabit Hassan","orcid":"https://orcid.org/0000-0001-7518-966X"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sabit Hassan","raw_affiliation_strings":["School of Computing and Information, University of Pittsburgh, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information, University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022279488","display_name":"Shammur Absar Chowdhury","orcid":"https://orcid.org/0000-0002-1331-2543"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Shammur Absar Chowdhury","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0002-1331-2543","affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102924560"],"corresponding_institution_ids":["https://openalex.org/I4210144839"],"apc_list":null,"apc_paid":null,"fwci":7.8894,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.98081426,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"29","issue":"6","first_page":"1436","last_page":"1457"},"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":0.9677548408508301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8524245619773865},{"id":"https://openalex.org/keywords/sarcasm","display_name":"Sarcasm","score":0.7118892073631287},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5630515813827515},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.562676191329956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.560152530670166},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.48594653606414795},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42098358273506165},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4207381010055542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36944371461868286},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19156965613365173}],"concepts":[{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.9677548408508301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8524245619773865},{"id":"https://openalex.org/C2776207355","wikidata":"https://www.wikidata.org/wiki/Q191035","display_name":"Sarcasm","level":3,"score":0.7118892073631287},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5630515813827515},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.562676191329956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.560152530670166},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.48594653606414795},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42098358273506165},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4207381010055542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36944371461868286},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19156965613365173},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C2779975665","wikidata":"https://www.wikidata.org/wiki/Q131361","display_name":"Irony","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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":2,"locations":[{"id":"doi:10.1017/s1351324923000402","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000402","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/2C1DFD708D4EE24B4E22C5664BD9B2E1/S1351324923000402a.pdf/div-class-title-emojis-as-anchors-to-detect-arabic-offensive-language-and-hate-speech-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/26661514","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Emojis_as_anchors_to_detect_Arabic_offensive_language_and_hate_speech/26661514","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1017/s1351324923000402","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000402","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/2C1DFD708D4EE24B4E22C5664BD9B2E1/S1351324923000402a.pdf/div-class-title-emojis-as-anchors-to-detect-arabic-offensive-language-and-hate-speech-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385723172.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W91442942","https://openalex.org/W2030978449","https://openalex.org/W2073560314","https://openalex.org/W2164641162","https://openalex.org/W2164777277","https://openalex.org/W2282821441","https://openalex.org/W2736566371","https://openalex.org/W2747187574","https://openalex.org/W2898401058","https://openalex.org/W2946706859","https://openalex.org/W2949340035","https://openalex.org/W2971150411","https://openalex.org/W3010139421","https://openalex.org/W3013437827","https://openalex.org/W3035390927","https://openalex.org/W3097400019","https://openalex.org/W3106460864","https://openalex.org/W3114526288","https://openalex.org/W3116878825","https://openalex.org/W3133440961","https://openalex.org/W4230281441","https://openalex.org/W4233907442","https://openalex.org/W4245193884","https://openalex.org/W4248473925","https://openalex.org/W4285537247","https://openalex.org/W4287121298","https://openalex.org/W4365800096","https://openalex.org/W6603689333","https://openalex.org/W6796711939"],"related_works":["https://openalex.org/W3046053481","https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287598411","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738"],"abstract_inverted_index":{"Abstract":[0],"We":[1,23,40,57,73,114,198],"introduce":[2],"a":[3,9,34,59,125,130],"generic,":[4],"language-independent":[5],"method":[6,44,156],"to":[7,32,65,193,207],"collect":[8,33],"large":[10,35],"percentage":[11],"of":[12,18,37,62,160,195],"offensive":[13,38,84,161,172],"and":[14,48,76,91,102,109,129,138,184,213],"hate":[15,87,103,177],"tweets":[16,47],"regardless":[17],"their":[19],"topics":[20],"or":[21,215],"genres.":[22],"harness":[24],"the":[25,30,42,79,97,151,167],"extralinguistic":[26],"information":[27],"embedded":[28],"in":[29,171,181,219],"emojis":[31,64],"number":[36],"tweets.":[39],"apply":[41],"proposed":[43],"on":[45,71,118,146],"Arabic":[46,81],"compare":[49],"it":[50],"with":[51],"English":[52],"tweets\u2014analyzing":[53],"key":[54],"cultural":[55],"differences.":[56],"observed":[58],"constant":[60],"usage":[61],"these":[63,147],"represent":[66],"offensiveness":[67,101],"throughout":[68],"different":[69,106,127],"timespans":[70],"Twitter.":[72],"manually":[74],"annotate":[75],"publicly":[77],"release":[78],"largest":[80],"dataset":[82,98,122,132],"for":[83,99,140,176],",":[85,89],"fine-grained":[86],"speech":[88,104],"vulgar,":[90],"violence":[92,182],"content.":[93],"Furthermore,":[94],"we":[95],"benchmark":[96],"detecting":[100],"using":[105,124,154],"transformer":[107,203],"architectures":[108],"perform":[110],"in-depth":[111],"linguistic":[112],"analysis.":[113],"evaluate":[115],"our":[116,155],"models":[117,204],"external":[119],"datasets\u2014a":[120],"Twitter":[121],"collected":[123,153],"completely":[126],"method,":[128],"multi-platform":[131],"containing":[133],"comments":[134],"from":[135],"Twitter,":[136],"YouTube,":[137],"Facebook,":[139],"assessing":[141],"generalization":[142],"capability.":[143],"Competitive":[144],"results":[145],"datasets":[148],"suggest":[149],"that":[150,189,200],"data":[152,221],"capture":[157],"universal":[158],"characteristics":[159],"language.":[162],"Our":[163],"findings":[164],"also":[165],"highlight":[166],"common":[168,174,186],"words":[169],"used":[170],"communications,":[173],"targets":[175],"speech,":[178],"specific":[179],"patterns":[180],"tweets,":[183],"pinpoint":[185],"classification":[187],"errors":[188],"can":[190],"be":[191],"attributed":[192],"limitations":[194],"NLP":[196],"models.":[197],"observe":[199],"even":[201],"state-of-the-art":[202],"may":[205],"fail":[206],"take":[208],"into":[209],"account":[210],"culture,":[211],"background,":[212],"context":[214],"understand":[216],"nuances":[217],"present":[218],"real-world":[220],"such":[222],"as":[223],"sarcasm.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":4}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}
