{"id":"https://openalex.org/W4415463286","doi":"https://doi.org/10.7717/peerj-cs.3127","title":"Towards boosting unlabeled text corpora for Arabic dialect identification","display_name":"Towards boosting unlabeled text corpora for Arabic dialect identification","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4415463286","doi":"https://doi.org/10.7717/peerj-cs.3127"},"language":"en","primary_location":{"id":"doi:10.7717/peerj-cs.3127","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj-cs.3127","pdf_url":"https://peerj.com/articles/cs-3127.pdf","source":{"id":"https://openalex.org/S4210178049","display_name":"PeerJ Computer Science","issn_l":"2376-5992","issn":["2376-5992"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://peerj.com/articles/cs-3127.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025341361","display_name":"Mohammed Abdelmajeed","orcid":"https://orcid.org/0000-0002-3001-1662"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mohammed Abdelmajeed","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680284","display_name":"Jiangbin Zheng","orcid":"https://orcid.org/0000-0003-0623-584X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Jiangbin","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087283637","display_name":"Murtadha Ahmed","orcid":"https://orcid.org/0000-0002-0741-0710"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Murtadha Ahmed","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042796984","display_name":"Mohammed Abaker","orcid":"https://orcid.org/0000-0001-8546-9470"},"institutions":[{"id":"https://openalex.org/I82952536","display_name":"King Khalid University","ror":"https://ror.org/052kwzs30","country_code":"SA","type":"education","lineage":["https://openalex.org/I82952536"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohammed Abaker","raw_affiliation_strings":["Department of Computer Science, Applied College, King Khalid University, Muhayil, Asir, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Applied College, King Khalid University, Muhayil, Asir, Saudi Arabia","institution_ids":["https://openalex.org/I82952536"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025341361"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":{"value":1395,"currency":"USD","value_usd":1395},"apc_paid":{"value":1395,"currency":"USD","value_usd":1395},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15672255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"e3127","last_page":"e3127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9975000023841858,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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/boosting","display_name":"Boosting (machine learning)","score":0.7272999882698059},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6629999876022339},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.5429999828338623},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4433000087738037},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.39629998803138733},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3402000069618225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744700014591217},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7272999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7085000276565552},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6629999876022339},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6431999802589417},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5429999828338623},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.39629998803138733},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.7717/peerj-cs.3127","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj-cs.3127","pdf_url":"https://peerj.com/articles/cs-3127.pdf","source":{"id":"https://openalex.org/S4210178049","display_name":"PeerJ Computer Science","issn_l":"2376-5992","issn":["2376-5992"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1ab3d1b147e04563864e8754dfaf881b","is_oa":true,"landing_page_url":"https://doaj.org/article/1ab3d1b147e04563864e8754dfaf881b","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PeerJ Computer Science, Vol 11, p e3127 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.7717/peerj-cs.3127","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj-cs.3127","pdf_url":"https://peerj.com/articles/cs-3127.pdf","source":{"id":"https://openalex.org/S4210178049","display_name":"PeerJ Computer Science","issn_l":"2376-5992","issn":["2376-5992"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5326727738","display_name":null,"funder_award_id":"RGP2/569/46","funder_id":"https://openalex.org/F33954902","funder_display_name":"Deanship of Scientific Research, King Khalid University"},{"id":"https://openalex.org/G5905890332","display_name":null,"funder_award_id":"61901388","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F33954902","display_name":"Deanship of Scientific Research, King Khalid University","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324433","display_name":"King Khalid University","ror":"https://ror.org/052kwzs30"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415463286.pdf","grobid_xml":"https://content.openalex.org/works/W4415463286.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2160802179","https://openalex.org/W2295824561","https://openalex.org/W2770803436","https://openalex.org/W2782027603","https://openalex.org/W2897077948","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2996428491","https://openalex.org/W2996580882","https://openalex.org/W3041687854","https://openalex.org/W3097571385","https://openalex.org/W3103646405","https://openalex.org/W4287727940","https://openalex.org/W4287993739","https://openalex.org/W4292779060","https://openalex.org/W4297663785","https://openalex.org/W4327810158","https://openalex.org/W4384918448","https://openalex.org/W4388979610","https://openalex.org/W4399073714","https://openalex.org/W4400516964","https://openalex.org/W4401537240","https://openalex.org/W4404791720","https://openalex.org/W4409084566"],"related_works":[],"abstract_inverted_index":{"Arabic":[0,15,39,55],"dialect":[1,11],"identification":[2],"(ADI)":[3],"aims":[4],"to":[5,60,107,131,161],"automatically":[6],"determine":[7],"the":[8,49],"specific":[9],"regional":[10],"of":[12,52,68,159],"a":[13,92,109],"given":[14],"text.":[16],"State-of-the-art":[17],"ADI":[18,133,141],"solutions":[19],"often":[20],"rely":[21],"on":[22,36,45,139],"fine-tuning":[23],"Arabic-specific":[24],"pre-trained":[25],"language":[26],"models":[27],"(PLMs).":[28],"Although":[29],"effective,":[30],"these":[31,88],"PLMs":[32],"are":[33,126],"predominantly":[34],"trained":[35],"modern":[37],"standard":[38],"(MSA),":[40],"which":[41,125],"limits":[42],"their":[43],"performance":[44,153],"dialectal":[46,113],"data.":[47,70],"Furthermore,":[48],"high":[50],"degree":[51],"similarity":[53],"among":[54],"dialects":[56],"makes":[57],"it":[58],"difficult":[59],"learn":[61],"accurate":[62],"dialect-specific":[63,123],"representations":[64],"without":[65],"large":[66],"volumes":[67],"labeled":[69],"However,":[71],"labeling":[72],"such":[73],"data":[74,106],"is":[75],"both":[76],"costly":[77],"and":[78,142,165],"labor-intensive,":[79],"particularly":[80],"for":[81],"low-resource":[82],"languages":[83],"like":[84],"Arabic.":[85],"To":[86],"address":[87],"challenges,":[89],"we":[90],"propose":[91],"self-training":[93],"neural":[94],"approach":[95,138],"that":[96,111,147],"independently":[97],"learns":[98],"Dialectal":[99],"Indicators":[100],".":[101],"Our":[102],"method":[103,149],"leverages":[104],"unlabeled":[105],"construct":[108],"matrix":[110,121],"captures":[112],"tokens":[114],"frequently":[115],"co-occurring":[116],"in":[117,163,167],"similar":[118],"contexts.":[119],"This":[120],"provides":[122],"representations,":[124],"integrated":[127],"with":[128],"PLM":[129,152],"outputs":[130],"enhance":[132],"performance.":[134],"We":[135],"evaluate":[136],"our":[137,148],"multiple":[140],"related":[143],"datasets.":[144],"Results":[145],"show":[146],"significantly":[150],"improves":[151],"over":[154],"direct":[155],"fine-tuning,":[156],"achieving":[157],"gains":[158],"up":[160],"36.2%":[162],"accuracy":[164],"11.52%":[166],"macro-F1-score.":[168]},"counts_by_year":[],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-24T00:00:00"}