{"id":"https://openalex.org/W4401042116","doi":"https://doi.org/10.18653/v1/2024.vardial-1.4","title":"How Well Do Tweets Represent Sub-Dialects of Egyptian Arabic?","display_name":"How Well Do Tweets Represent Sub-Dialects of Egyptian Arabic?","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401042116","doi":"https://doi.org/10.18653/v1/2024.vardial-1.4"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.vardial-1.4","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.4","pdf_url":"https://aclanthology.org/2024.vardial-1.4.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.vardial-1.4.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106203186","display_name":"Mai Mohamed Eida","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mai Mohamed Eida","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114124244","display_name":"Mayar Nassar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mayar Nassar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063420865","display_name":"Jonathan Dunn","orcid":"https://orcid.org/0000-0002-1189-1908"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Dunn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106203186"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3299,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64053882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9916999936103821,"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":0.9916999936103821,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13623","display_name":"Linguistic Studies and Language Acquisition","score":0.9828000068664551,"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/arabic","display_name":"Arabic","score":0.7709879875183105},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6908785104751587},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6063776016235352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.461020827293396},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4162832796573639}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7709879875183105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6908785104751587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6063776016235352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.461020827293396},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4162832796573639},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.vardial-1.4","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.4","pdf_url":"https://aclanthology.org/2024.vardial-1.4.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.vardial-1.4","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.4","pdf_url":"https://aclanthology.org/2024.vardial-1.4.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401042116.pdf","grobid_xml":"https://content.openalex.org/works/W4401042116.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4249048193","https://openalex.org/W3204019825"],"abstract_inverted_index":{"How":[0],"well":[1],"does":[2],"naturally-occurring":[3],"digital":[4],"text,":[5],"such":[6],"as":[7,37,51],"tweets,":[8,56],"represent":[9,86,93,113],"sub-dialects":[10,87,94],"of":[11,71,77,88,96,106],"Egyptian":[12,22,27],"Arabic":[13,23,28],"(EA)?This":[14],"paper":[15],"focuses":[16],"on":[17,108],"two":[18],"EA":[19,89],"sub-dialects:":[20],"Cairene":[21,98],"(CEA)":[24],"and":[25,74],"Sa'idi":[26],"(SEA).We":[29],"use":[30],"morphological":[31],"markers":[32,48,59,73],"from":[33],"groundtruth":[34],"dialect":[35],"surveys":[36],"a":[38,69],"distance":[39],"measure":[40],"across":[41,62],"four":[42],"geo-referenced":[43,55],"datasets.Results":[44],"show":[45,68],"that":[46,82],"CEA":[47,54,72],"are":[49,60],"prevalent":[50],"expected":[52],"in":[53],"while":[57],"SEA":[58,63],"limited":[61],"georeferenced":[64,109],"tweets.SEA":[65],"tweets":[66,110],"instead":[67],"prevalence":[70],"higher":[75],"usage":[76],"Modern":[78],"Standard":[79],"Arabic.We":[80],"conclude":[81],"corpora":[83],"intended":[84],"to":[85,112],"do":[90],"not":[91],"accurately":[92],"outside":[95],"the":[97,104],"variety.This":[99],"finding":[100],"calls":[101],"into":[102],"question":[103],"validity":[105],"relying":[107],"alone":[111],"dialectal":[114],"differences.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-27T08:22:11.395708","created_date":"2025-10-10T00:00:00"}