{"id":"https://openalex.org/W4389712439","doi":"https://doi.org/10.48550/arxiv.2312.07228","title":"Toxic language detection: a systematic review of Arabic datasets","display_name":"Toxic language detection: a systematic review of Arabic datasets","publication_year":2023,"publication_date":"2023-12-12","ids":{"openalex":"https://openalex.org/W4389712439","doi":"https://doi.org/10.48550/arxiv.2312.07228"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.07228","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.07228","pdf_url":"https://arxiv.org/pdf/2312.07228","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"review","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.07228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079157864","display_name":"Imene Bensalem","orcid":"https://orcid.org/0000-0002-2462-5967","observed_orcids":["https://orcid.org/0000-0002-2462-5967"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bensalem, Imene","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053947754","display_name":"Paolo Rosso","orcid":"https://orcid.org/0000-0002-8922-1242","observed_orcids":["https://orcid.org/0000-0002-8922-1242"]},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rosso, Paolo","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia ,","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062822407","display_name":"Hanane Zitouni","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zitouni, Hanane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0209,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.15288462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/toxic-language-detection","display_name":"toxic language detection","score":0.9760000109672546},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic language","score":0.8999999761581421},{"id":"https://openalex.org/keywords/annotated-data","display_name":"annotated dataset","score":0.8500000238418579},{"id":"https://openalex.org/keywords/dataset-evaluation","display_name":"dataset evaluation","score":0.5609999895095825}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7924027442932129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598748803138733},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6897695064544678},{"id":"https://openalex.org/C137981799","wikidata":"https://www.wikidata.org/wiki/Q1369184","display_name":"Reusability","level":3,"score":0.5235611796379089},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5111153721809387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4841240346431732},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4036775231361389},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.372974157333374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3321244716644287},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12398329377174377},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09605869650840759},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.07228","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.07228","pdf_url":"https://arxiv.org/pdf/2312.07228","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.07228","doi":"https://doi.org/10.48550/arxiv.2312.07228","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.07228","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.07228","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.07228","pdf_url":"https://arxiv.org/pdf/2312.07228","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality education"}],"study_designs":[{"id":"https://openalex.org/study-designs/systematic-review","display_name":"Systematic Review"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309815","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05"},{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"},{"id":"https://openalex.org/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389712439.pdf","grobid_xml":"https://content.openalex.org/works/W4389712439.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7154565485","https://openalex.org/W4416504162","https://openalex.org/W3186955206","https://openalex.org/W4388197554","https://openalex.org/W2972463128","https://openalex.org/W4409473974","https://openalex.org/W4403104564","https://openalex.org/W4362647463","https://openalex.org/W3124373221","https://openalex.org/W2747187574"],"abstract_inverted_index":{"The":[0],"detection":[1],"of":[2,15,42,55,100,106],"toxic":[3,48],"language":[4,8],"in":[5,17,112],"the":[6,22,28,98,101,104,107],"Arabic":[7,43],"has":[9,31],"emerged":[10],"as":[11],"an":[12],"active":[13],"area":[14],"research":[16,95,102],"recent":[18],"years,":[19],"and":[20,59,63,80,90],"reviewing":[21],"existing":[23,88],"datasets":[24,44,58,109],"employed":[25],"for":[26,93],"training":[27],"developed":[29],"solutions":[30],"become":[32],"a":[33,39,53,65,113],"pressing":[34],"need.":[35],"This":[36,82],"paper":[37],"offers":[38],"comprehensive":[40],"survey":[41],"focused":[45],"on":[46],"online":[47],"language.":[49],"We":[50],"systematically":[51],"gathered":[52],"total":[54],"54":[56],"available":[57],"their":[60],"corresponding":[61],"papers":[62],"conducted":[64],"thorough":[66],"analysis,":[67],"considering":[68],"18":[69],"criteria":[70],"across":[71],"four":[72],"primary":[73],"dimensions:":[74],"availability":[75],"details,":[76],"content,":[77],"annotation":[78],"process,":[79],"reusability.":[81],"analysis":[83],"enabled":[84],"us":[85],"to":[86],"identify":[87],"gaps":[89],"make":[91],"recommendations":[92],"future":[94],"works.":[96],"For":[97],"convenience":[99],"community,":[103],"list":[105],"analysed":[108],"is":[110],"maintained":[111],"GitHub":[114],"repository":[115],"(https://github.com/Imene1/Arabic-toxic-language).":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2023-12-14T00:00:00"}
