{"id":"https://openalex.org/W2103195385","doi":"https://doi.org/10.1145/2632188.2632207","title":"Automatic identification of arabic dialects in social media","display_name":"Automatic identification of arabic dialects in social media","publication_year":2014,"publication_date":"2014-07-11","ids":{"openalex":"https://openalex.org/W2103195385","doi":"https://doi.org/10.1145/2632188.2632207","mag":"2103195385"},"language":"en","primary_location":{"id":"doi:10.1145/2632188.2632207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2632188.2632207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the first international workshop on Social media retrieval and analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030866856","display_name":"Fatiha Sadat","orcid":"https://orcid.org/0000-0002-9292-722X"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Fatiha Sadat","raw_affiliation_strings":["UQAM, Montreal, PQ, Canada"],"affiliations":[{"raw_affiliation_string":"UQAM, Montreal, PQ, Canada","institution_ids":["https://openalex.org/I159129438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021222942","display_name":"Farnazeh Kazemi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farnazeh Kazemi","raw_affiliation_strings":["NLP Technologies Inc., Montreal, PQ, Canada"],"affiliations":[{"raw_affiliation_string":"NLP Technologies Inc., Montreal, PQ, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045732893","display_name":"Atefeh Farzindar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atefeh Farzindar","raw_affiliation_strings":["NLP Technologies Inc., Montreal, PQ, Canada"],"affiliations":[{"raw_affiliation_string":"NLP Technologies Inc., Montreal, PQ, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030866856"],"corresponding_institution_ids":["https://openalex.org/I159129438"],"apc_list":null,"apc_paid":null,"fwci":4.0901,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.94361809,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998000264167786,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.993399977684021,"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/T13155","display_name":"Digital Communication and Language","score":0.9728999733924866,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.80295330286026},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6982474327087402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6737325191497803},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6099369525909424},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5745131969451904},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5704285502433777},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5535441637039185},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.5458678007125854},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5185245275497437},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.4501098692417145},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4458259344100952},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.44291603565216064},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.41816988587379456},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.415279746055603},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.305044949054718},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.17897477746009827},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1367335021495819},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11316409707069397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80295330286026},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6982474327087402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6737325191497803},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6099369525909424},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5745131969451904},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5704285502433777},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5535441637039185},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5458678007125854},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5185245275497437},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4501098692417145},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4458259344100952},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.44291603565216064},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.41816988587379456},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.415279746055603},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.305044949054718},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.17897477746009827},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1367335021495819},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11316409707069397},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2632188.2632207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2632188.2632207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the first international workshop on Social media retrieval and analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W57814663","https://openalex.org/W112512090","https://openalex.org/W137260243","https://openalex.org/W1445897916","https://openalex.org/W1524281572","https://openalex.org/W1533946607","https://openalex.org/W1544567521","https://openalex.org/W1951381097","https://openalex.org/W1977195462","https://openalex.org/W2024338393","https://openalex.org/W2097743493","https://openalex.org/W2109704865","https://openalex.org/W2137498753","https://openalex.org/W2149684865","https://openalex.org/W2168576900","https://openalex.org/W2250414785","https://openalex.org/W2251404226","https://openalex.org/W2251657882","https://openalex.org/W2251862917","https://openalex.org/W2251986002","https://openalex.org/W2252212013","https://openalex.org/W2483327705","https://openalex.org/W2894859044","https://openalex.org/W2914151435","https://openalex.org/W4241982274","https://openalex.org/W6632118081"],"related_works":["https://openalex.org/W3110233274","https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W2057384730","https://openalex.org/W4307474317","https://openalex.org/W2008468404","https://openalex.org/W2147879411","https://openalex.org/W2132221452","https://openalex.org/W2624072012"],"abstract_inverted_index":{"Modern":[0],"Standard":[1],"Arabic":[2,10,12,28,117,140],"(MSA)":[3],"is":[4,128],"the":[5,48,75,114,146],"formal":[6],"language":[7,17,79],"in":[8,22,96],"most":[9,27],"countries.":[11],"Dialects":[13],"(AD)":[14],"or":[15],"daily":[16],"differs":[18],"from":[19,139],"MSA":[20,40,51],"especially":[21,38],"social":[23,29,65,97],"media":[24,30,66,98],"communication.":[25],"However,":[26],"texts":[31],"have":[32],"mixed":[33],"forms":[34],"and":[35,41,52,81,143],"many":[36],"variations":[37],"between":[39,50],"AD.":[42],"This":[43,126],"paper":[44],"aims":[45],"to":[46,141],"bridge":[47],"gap":[49],"AD":[53,59],"by":[54],"providing":[55],"a":[56,70,120,129,136],"framework":[57],"for":[58],"classification":[60],"using":[61,74],"probabilistic":[62],"models":[63,90],"across":[64],"datasets.":[67],"We":[68],"present":[69],"set":[71],"of":[72,88,124,135],"experiments":[73],"character":[76,109],"n-gram":[77],"Markov":[78],"model":[80,111],"Naive":[82,104],"Bayes":[83,105],"classifiers":[84],"with":[85,119],"detailed":[86],"examination":[87],"what":[89],"perform":[91],"best":[92],"under":[93],"different":[94,116],"conditions":[95],"context.":[99],"Experimental":[100],"results":[101],"show":[102],"that":[103],"classifier":[106],"based":[107],"on":[108],"bi-gram":[110],"can":[112],"identify":[113],"18":[115],"dialects":[118],"considerable":[121],"overall":[122],"accuracy":[123],"98%.":[125],"work":[127],"first-step":[130],"towards":[131],"an":[132],"ultimate":[133],"goal":[134],"translation":[137],"system":[138],"English":[142],"French,":[144],"within":[145],"ASMAT":[147],"project":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2026-01-30T23:17:42.513302","created_date":"2025-10-10T00:00:00"}