{"id":"https://openalex.org/W2806573136","doi":"https://doi.org/10.63317/4b9q46p2vs9o","title":"DART: A Large Dataset of Dialectal Arabic Tweets","display_name":"DART: A Large Dataset of Dialectal Arabic Tweets","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2806573136","doi":"https://doi.org/10.63317/4b9q46p2vs9o","mag":"2806573136"},"language":"en","primary_location":{"id":"doi:10.63317/4b9q46p2vs9o","doi":"https://doi.org/10.63317/4b9q46p2vs9o","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4b9q46p2vs9o","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2018/pdf/1013.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2018/pdf/1013.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029755780","display_name":"Israa Alsarsour","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Israa Alsarsour","raw_affiliation_strings":["Computer Science and Engineering Department , Qatar University , Doha , Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department , Qatar University , Doha , Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074471606","display_name":"Esraa Mohamed","orcid":"https://orcid.org/0000-0001-6877-9610","observed_orcids":["https://orcid.org/0000-0001-6877-9610"]},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Esraa Mohamed","raw_affiliation_strings":["Computer Science and Engineering Department , Qatar University , Doha , Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department , Qatar University , Doha , Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047381062","display_name":"Reem Suwaileh","orcid":"https://orcid.org/0000-0001-7341-1407","observed_orcids":["https://orcid.org/0000-0001-7341-1407"]},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Reem Suwaileh","raw_affiliation_strings":["Computer Science and Engineering Department , Qatar University , Doha , Qatar","Qatar University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department , Qatar University , Doha , Qatar","institution_ids":["https://openalex.org/I60342839"]},{"raw_affiliation_string":"Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032141720","display_name":"Tamer Elsayed","orcid":"https://orcid.org/0000-0001-5786-4668","observed_orcids":["https://orcid.org/0000-0001-5786-4668"]},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Tamer Elsayed","raw_affiliation_strings":["Qatar University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60342839"],"apc_list":null,"apc_paid":null,"fwci":2.0333,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.91009682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.6855000257492065,"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":0.6855000257492065,"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":0.08009999990463257,"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":0.03449999913573265,"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-dialects","display_name":"Arabic dialects","score":0.8859999775886536},{"id":"https://openalex.org/keywords/arabic-tweets","display_name":"Arabic tweets","score":0.828000009059906},{"id":"https://openalex.org/keywords/dialect-identification","display_name":"dialect identification","score":0.7070000171661377},{"id":"https://openalex.org/keywords/annotated-data","display_name":"annotated dataset","score":0.5619999766349792},{"id":"https://openalex.org/keywords/crowdsourced-annotation","display_name":"crowdsourced annotation","score":0.7279999852180481},{"id":"https://openalex.org/keywords/egyptian-arabic","display_name":"Egyptian Arabic","score":0.7839999794960022},{"id":"https://openalex.org/keywords/maghrebi-arabic","display_name":"Maghrebi Arabic","score":0.968999981880188},{"id":"https://openalex.org/keywords/levantine-arabic","display_name":"Levantine Arabic","score":0.9990000128746033},{"id":"https://openalex.org/keywords/gulf-arabic","display_name":"Gulf Arabic","score":0.9929999709129333},{"id":"https://openalex.org/keywords/iraqi-arabic","display_name":"Iraqi Arabic","score":0.996999979019165},{"id":"https://openalex.org/keywords/inter-annotator-agreement","display_name":"inter-annotator agreement","score":0.9020000100135803},{"id":"https://openalex.org/keywords/social-media-text","display_name":"social media text","score":0.4410000145435333}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.8023487329483032},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5897283554077148},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.5615292191505432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4659847617149353},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.41375356912612915},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3231821060180664},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3180808126926422},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2194596529006958},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17408505082130432},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.09223806858062744},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/4b9q46p2vs9o","doi":"https://doi.org/10.63317/4b9q46p2vs9o","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4b9q46p2vs9o","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2018/pdf/1013.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:qspace.qu.edu.qa:10576/15265","doi":null,"is_oa":false,"landing_page_url":"https://www.scopus.com/inward/record.uri?eid=2-s2.0-85059884453&partnerID=40&md5=b3a515e144e74a7cb819868d62d1b814","pdf_url":null,"source":{"id":"https://openalex.org/S4306400014","display_name":"Qatar University QSpace (Qatar University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I60342839","host_organization_name":"Qatar University","host_organization_lineage":["https://openalex.org/I60342839"],"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":"Conference"},{"id":"mag:2806573136","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/L18-1579.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-3","norway-2","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation","raw_type":null}],"best_oa_location":{"id":"doi:10.63317/4b9q46p2vs9o","doi":"https://doi.org/10.63317/4b9q46p2vs9o","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4b9q46p2vs9o","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2018/pdf/1013.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"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/W2806573136.pdf","grobid_xml":"https://content.openalex.org/works/W2806573136.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W137989762","https://openalex.org/W1975879668","https://openalex.org/W1977195462","https://openalex.org/W2109704865","https://openalex.org/W2123777430","https://openalex.org/W2250378459","https://openalex.org/W2250783208","https://openalex.org/W2251635021","https://openalex.org/W2251867433","https://openalex.org/W2251986002","https://openalex.org/W2252067490","https://openalex.org/W2747566258"],"related_works":["https://openalex.org/W3120314993","https://openalex.org/W3025939269","https://openalex.org/W2805089673","https://openalex.org/W2986081116","https://openalex.org/W3154301048","https://openalex.org/W2250278916","https://openalex.org/W2806092253","https://openalex.org/W3191380211","https://openalex.org/W2806709046","https://openalex.org/W4399073714"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,79],"present":[4],"a":[5,62],"new":[6],"large":[7],"manually-annotated":[8],"multi-dialect":[9],"dataset":[10,22,56,89],"of":[11,40,53,64,87,99,130],"Arabic":[12,41],"tweets":[13,26,59,70],"that":[14,27,60,78,104],"is":[15,34],"publicly":[16],"available.The":[17],"Dialectal":[18],"ARabic":[19],"Tweets":[20],"(DART)":[21],"has":[23],"about":[24],"25K":[25],"are":[28],"annotated":[29],"via":[30],"crowdsourcing":[31],"and":[32,47,96,114,123,136],"it":[33],"well-balanced":[35],"over":[36],"five":[37],"main":[38],"groups":[39],"dialects:":[42],"Egyptian,":[43,112],"Maghrebi,":[44],"Levantine,":[45],"Gulf,":[46,113],"Iraqi.The":[48],"paper":[49],"outlines":[50],"the":[51,55,69,72,82,85,88,93,97,100,111,121,128],"pipeline":[52],"constructing":[54],"from":[57,90],"crawling":[58],"match":[61],"list":[63],"dialect":[65,116],"phrases":[66],"to":[67],"annotating":[68],"by":[71],"crowd.We":[73],"also":[74],"touch":[75],"some":[76],"challenges":[77],"face":[80],"during":[81],"process.We":[83],"evaluate":[84],"quality":[86],"two":[91,133],"perspectives:":[92],"inter-annotator":[94],"agreement":[95],"accuracy":[98],"final":[101],"labels.Results":[102],"show":[103],"both":[105],"measures":[106],"were":[107],"substantially":[108],"high":[109],"for":[110,120],"Levantine":[115],"groups,":[117],"but":[118],"lower":[119],"Iraqi":[122],"Maghrebi":[124],"dialects,":[125],"which":[126],"indicates":[127],"difficulty":[129],"identifying":[131],"those":[132],"dialects":[134],"manually":[135],"hence":[137],"automatically.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2018-06-13T00:00:00"}
