{"id":"https://openalex.org/W4408399575","doi":"https://doi.org/10.1109/access.2025.3551161","title":"\u201cDiwan\u201d: Constructing the Largest Annotated Corpus for Arabic Poetry","display_name":"\u201cDiwan\u201d: Constructing the Largest Annotated Corpus for Arabic Poetry","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408399575","doi":"https://doi.org/10.1109/access.2025.3551161"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3551161","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3551161","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3551161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012989030","display_name":"Badriyya B. Al-onazi","orcid":"https://orcid.org/0000-0001-7206-4896"},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Badriyya B. Al-Onazi","raw_affiliation_strings":["Department of Language Preparation, Arabic Language Teaching Institute, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Language Preparation, Arabic Language Teaching Institute, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116607481","display_name":"Wadee A. Nashir","orcid":null},"institutions":[{"id":"https://openalex.org/I118692353","display_name":"University of Science and Technology","ror":"https://ror.org/05bj7sh33","country_code":"YE","type":"education","lineage":["https://openalex.org/I118692353"]}],"countries":["YE"],"is_corresponding":false,"raw_author_name":"Wadee A. Nashir","raw_affiliation_strings":["Department of Computer Science, Faculty of Computing and Information Technology, University of Science and Technology, Sana’a, Yemen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computing and Information Technology, University of Science and Technology, Sana’a, Yemen","institution_ids":["https://openalex.org/I118692353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018170338","display_name":"Asma A. Al-Shargabi","orcid":"https://orcid.org/0000-0002-6572-2923"},"institutions":[{"id":"https://openalex.org/I156216236","display_name":"Qassim University","ror":"https://ror.org/01wsfe280","country_code":"SA","type":"education","lineage":["https://openalex.org/I156216236"]},{"id":"https://openalex.org/I4210092650","display_name":"Buraydah Colleges","ror":"https://ror.org/00j0krs40","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210092650"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Asma A. Al-Shargabi","raw_affiliation_strings":["Department of Information Technology, Collage of Computer, Qassim University, Buraydah, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-6572-2923","affiliations":[{"raw_affiliation_string":"Department of Information Technology, Collage of Computer, Qassim University, Buraydah, Saudi Arabia","institution_ids":["https://openalex.org/I156216236","https://openalex.org/I4210092650"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":14.0235,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98522531,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"58927","last_page":"58941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14210","display_name":"Historical and Linguistic Studies","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14210","display_name":"Historical and Linguistic Studies","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10794","display_name":"Islamic Studies and History","score":0.9675999879837036,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9513999819755554,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7951256036758423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512753009796143},{"id":"https://openalex.org/keywords/poetry","display_name":"Poetry","score":0.6434409022331238},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6288555860519409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5282641649246216},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3663163185119629},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08648461103439331}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7951256036758423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512753009796143},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.6434409022331238},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6288555860519409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5282641649246216},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3663163185119629},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08648461103439331}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3551161","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3551161","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:98f2eb4f9203424cb4eb407d16b882f6","is_oa":true,"landing_page_url":"https://doaj.org/article/98f2eb4f9203424cb4eb407d16b882f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 58927-58941 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3551161","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3551161","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1329085646","display_name":null,"funder_award_id":"PNURSP2024R 263","funder_id":"https://openalex.org/F4320322484","funder_display_name":"Princess Nourah Bint Abdulrahman University"}],"funders":[{"id":"https://openalex.org/F4320322484","display_name":"Princess Nourah Bint Abdulrahman University","ror":"https://ror.org/05b0cyh02"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2015930392","https://openalex.org/W2282838287","https://openalex.org/W2585345551","https://openalex.org/W2810470336","https://openalex.org/W2922193513","https://openalex.org/W2970814728","https://openalex.org/W2982556300","https://openalex.org/W3010004153","https://openalex.org/W3016620431","https://openalex.org/W3016962737","https://openalex.org/W3030753999","https://openalex.org/W3108561698","https://openalex.org/W3112961516","https://openalex.org/W3126159292","https://openalex.org/W3128072365","https://openalex.org/W3166011548","https://openalex.org/W3203646744","https://openalex.org/W4200603376","https://openalex.org/W4212824786","https://openalex.org/W4223988959","https://openalex.org/W4246033371","https://openalex.org/W4366829432","https://openalex.org/W4387485662","https://openalex.org/W4400498617","https://openalex.org/W4401879795","https://openalex.org/W6601355063","https://openalex.org/W6606975796","https://openalex.org/W6691383730","https://openalex.org/W6691620099","https://openalex.org/W6763181217","https://openalex.org/W6854459692","https://openalex.org/W6862032589","https://openalex.org/W6921482624"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Arabic":[3,26,45,97,166,210,254],"natural":[4],"language":[5,17],"processing":[6],"has":[7,146,202],"achieved":[8],"remarkable":[9],"advancements,":[10],"particularly":[11],"with":[12,44],"the":[13,22,74,91,107,268],"advent":[14],"of":[15,24,109,121,219,223,253,271],"large":[16],"models":[18,38],"that":[19,215],"have":[20],"enhanced":[21],"analysis":[23,81,238,241,270],"diverse":[25],"texts,":[27],"including":[28],"literary":[29,274],"and":[30,56,69,71,93,105,127,141,157,160,168,181,198,225,231,239,261,266],"artistic":[31],"works":[32],"such":[33,189],"as":[34,177,190],"poetry.":[35,169],"However,":[36],"these":[37],"encounter":[39],"specific":[40],"challenges":[41],"when":[42],"dealing":[43],"poetry,":[46,255],"which":[47],"is":[48,229],"characterized":[49],"by":[50],"complex":[51],"metrical":[52,194],"structures,":[53,136],"varied":[54],"themes,":[55],"unique":[57],"linguistic":[58,139],"intricacies.":[59],"Currently":[60],"available":[61],"poetry":[62,98,122,192],"corpora":[63,208],"are":[64],"often":[65],"limited":[66],"in":[67,112,165,187,221,233],"scope":[68],"depth,":[70],"typically":[72],"lack":[73],"comprehensive":[75],"coverage":[76],"required":[77],"for":[78,184,209,250,263],"sophisticated":[79],"computational":[80,251],"tasks.":[82],"To":[83],"address":[84],"this":[85,87,113,212,272],"gap,":[86],"paper":[88],"introduces":[89],"\u201cDiwan,\u201d":[90],"largest":[92],"most":[94],"precise":[95],"annotated":[96],"dataset/corpus,":[99],"designed":[100],"to":[101,132,242],"support":[102],"scientific":[103],"research":[104,186],"facilitate":[106],"development":[108],"AI":[110],"applications":[111,265],"domain.":[114],"\u201cDiwan\u201d":[115,201,216,228],"comprises":[116],"approximately":[117],"14":[118],"million":[119],"verses":[120],"across":[123],"16":[124],"major":[125],"categories":[126],"includes":[128],"detailed":[129],"annotations":[130],"related":[131],"poetic":[133],"genres,":[134],"prosodic":[135],"thematic":[137,196],"content,":[138],"patterns,":[140],"poet-specific":[142],"metadata.":[143],"This":[144],"dataset/corpus":[145],"been":[147,203],"meticulously":[148],"curated":[149],"using":[150],"advanced":[151],"data":[152],"collection":[153],"methods,":[154],"rigorous":[155],"normalization":[156],"annotation":[158,173],"protocols,":[159],"expert":[161],"oversight":[162],"from":[163],"specialists":[164],"prosody":[167],"By":[170,245],"leveraging":[171],"intelligent":[172,264],"algorithms,":[174],"Diwan":[175,256],"serves":[176],"a":[178,234],"foundational":[179],"resource":[180],"benchmark":[182],"dataset":[183],"advancing":[185],"fields":[188],"automatic":[191],"generation,":[193],"analysis,":[195],"classification,":[197],"plagiarism":[199],"detection.":[200],"compared":[204],"against":[205],"4":[206],"leading":[207],"poetry;":[211],"comparison":[213],"proves":[214],"outperforms":[217],"all":[218],"them":[220],"terms":[222],"scope,":[224],"depth.":[226],"Besides,":[227],"constructed":[230],"structured":[232],"way":[235],"enables":[236],"AI-powered":[237],"deep-learning-based":[240],"work":[243],"accurately.":[244],"providing":[246],"an":[247],"unprecedented":[248],"foundation":[249],"exploration":[252],"opens":[257],"up":[258],"new":[259],"avenues":[260],"possibilities":[262],"promotes":[267],"digital":[269],"rich":[273],"heritage.":[275]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-03-14T00:00:00"}