{"id":"https://openalex.org/W2986081116","doi":"https://doi.org/10.26615/978-954-452-056-4_023","title":"A Fine-Grained Annotated Multi-Dialectal Arabic Corpus","display_name":"A Fine-Grained Annotated Multi-Dialectal Arabic Corpus","publication_year":2019,"publication_date":"2019-10-22","ids":{"openalex":"https://openalex.org/W2986081116","doi":"https://doi.org/10.26615/978-954-452-056-4_023","mag":"2986081116"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-056-4_023","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_023","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_023","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/978-954-452-056-4_023","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029753508","display_name":"Anis Charfi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Anis Charfi","raw_affiliation_strings":["Information Systems Carnegie Mellon University in Qatar"],"affiliations":[{"raw_affiliation_string":"Information Systems Carnegie Mellon University in Qatar","institution_ids":["https://openalex.org/I4210089979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047390057","display_name":"Wajdi Zaghouani","orcid":"https://orcid.org/0000-0003-1521-5568"},"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":"Wajdi Zaghouani","raw_affiliation_strings":["College of Humanities and Social Sciences Hamad Bin Khalifa University Qatar"],"affiliations":[{"raw_affiliation_string":"College of Humanities and Social Sciences Hamad Bin Khalifa University Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086768434","display_name":"Syed Hassan Mehdi","orcid":"https://orcid.org/0009-0009-3333-8802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Syed Hassan Mehdi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074471606","display_name":"Esraa Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089979","display_name":"Carnegie Mellon University Qatar","ror":"https://ror.org/00az5dt38","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210089979","https://openalex.org/I74973139"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Esraa Mohamed","raw_affiliation_strings":["Information Systems Carnegie Mellon University in Qatar"],"affiliations":[{"raw_affiliation_string":"Information Systems Carnegie Mellon University in Qatar","institution_ids":["https://openalex.org/I4210089979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029753508"],"corresponding_institution_ids":["https://openalex.org/I4210089979"],"apc_list":null,"apc_paid":null,"fwci":0.1445,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59733323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"198","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9947999715805054,"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/annotation","display_name":"Annotation","score":0.9133219122886658},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7557732462882996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7547416687011719},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6850931644439697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5693331360816956},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5438587665557861},{"id":"https://openalex.org/keywords/agreement","display_name":"Agreement","score":0.4752925634384155},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.444394052028656},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.4355523884296417},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.4354492425918579},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.37446093559265137},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33872750401496887}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.9133219122886658},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7557732462882996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547416687011719},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6850931644439697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5693331360816956},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5438587665557861},{"id":"https://openalex.org/C2776818064","wikidata":"https://www.wikidata.org/wiki/Q829903","display_name":"Agreement","level":2,"score":0.4752925634384155},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.444394052028656},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.4355523884296417},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.4354492425918579},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37446093559265137},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33872750401496887},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26615/978-954-452-056-4_023","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_023","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_023","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-056-4_023","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_023","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_023","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4122008771","display_name":null,"funder_award_id":"9-175-1-033","funder_id":"https://openalex.org/F4320332753","funder_display_name":"Qatar National Research Fund"},{"id":"https://openalex.org/G663536635","display_name":null,"funder_award_id":"NPRP 9-175-1-033","funder_id":"https://openalex.org/F4320332753","funder_display_name":"Qatar National Research Fund"}],"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/W2986081116.pdf","grobid_xml":"https://content.openalex.org/works/W2986081116.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W19634895","https://openalex.org/W41492599","https://openalex.org/W49748952","https://openalex.org/W114284868","https://openalex.org/W137989762","https://openalex.org/W1978174332","https://openalex.org/W2117202778","https://openalex.org/W2147272182","https://openalex.org/W2250625307","https://openalex.org/W2250732891","https://openalex.org/W2250783208","https://openalex.org/W2250784517","https://openalex.org/W2250816155","https://openalex.org/W2250868350","https://openalex.org/W2252067490","https://openalex.org/W2572275374","https://openalex.org/W2805431570","https://openalex.org/W2806092253","https://openalex.org/W2806573136","https://openalex.org/W2806962830","https://openalex.org/W2888364742","https://openalex.org/W2889395474","https://openalex.org/W2900704097","https://openalex.org/W2963943537","https://openalex.org/W4289673860","https://openalex.org/W4300167661"],"related_works":["https://openalex.org/W2251910928","https://openalex.org/W4361282947","https://openalex.org/W2250493512","https://openalex.org/W4392318734","https://openalex.org/W2620283452","https://openalex.org/W4322750817","https://openalex.org/W4400896925","https://openalex.org/W2801712537","https://openalex.org/W4396221470","https://openalex.org/W2626378867"],"abstract_inverted_index":{"We":[0,98,149],"present":[1],"ARAP-Tweet":[2],"2.0,":[3],"a":[4,123],"corpus":[5,32,79,119],"of":[6,16,38,76,104,135,143],"5":[7],"million":[8,14],"dialectal":[9,84],"Arabic":[10],"tweets":[11],"and":[12,42,55,64,66,69,94,120,138,146],"50":[13],"words":[15],"about":[17],"3000":[18],"Twitter":[19],"users":[20],"from":[21,81],"17":[22],"Arab":[23],"countries.":[24],"Compared":[25],"to":[26,52,86,90,116],"the":[27,30,39,43,74,78,83,88,102,105,109,117,141],"first":[28],"version,":[29],"new":[31],"has":[33],"significant":[34],"improvements":[35],"in":[36],"terms":[37],"data":[40],"volume":[41],"annotation":[44,106,142],"quality.":[45],"It":[46],"is":[47],"fully":[48],"balanced":[49],"with":[50,130],"respect":[51],"dialect,":[53,145],"gender,":[54,144],"three":[56],"age":[57,147],"groups:":[58],"under":[59],"25":[60,63],"years,":[61],"between":[62],"34,":[65],"35":[67],"years":[68],"above.":[70],"This":[71],"paper":[72],"describes":[73],"process":[75],"creating":[77],"starting":[80],"gathering":[82],"phrases":[85],"find":[87],"users,":[89],"annotating":[91],"their":[92,96],"accounts":[93],"retrieving":[95],"tweets.":[97],"also":[99,150],"report":[100],"on":[101],"evaluation":[103],"quality":[107],"using":[108],"inter-annotator":[110],"agreement":[111],"measures":[112],"which":[113],"were":[114,128],"applied":[115],"whole":[118],"not":[121],"just":[122],"subset.":[124],"The":[125],"obtained":[126],"results":[127],"substantial":[129],"average":[131],"Cohens":[132],"Kappa":[133],"values":[134],"0.99,":[136],"0.92,":[137],"0.88":[139],"for":[140],"respectively.":[148],"discuss":[151],"some":[152],"challenges":[153],"encountered":[154],"when":[155],"developing":[156],"this":[157],"corpus.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-11-22T00:00:00"}
