{"id":"https://openalex.org/W7202378024","doi":"https://doi.org/10.5334/johd.572","title":"Noor-Sharaye v.1. A Benchmark Dataset of Complex Words for Evaluating Arabic Analyzers","display_name":"Noor-Sharaye v.1. A Benchmark Dataset of Complex Words for Evaluating Arabic Analyzers","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7202378024","doi":"https://doi.org/10.5334/johd.572"},"language":"en","primary_location":{"id":"doi:10.5334/johd.572","doi":"https://doi.org/10.5334/johd.572","is_oa":true,"landing_page_url":"https://doi.org/10.5334/johd.572","pdf_url":"https://openhumanitiesdata.metajnl.com/articles/572/files/6a7db75f2697f.pdf","source":{"id":"https://openalex.org/S4210240912","display_name":"Journal of Open Humanities Data","issn_l":"2059-481X","issn":["2059-481X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","erih-plus","jufo-1","norway-1","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Humanities Data","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://openhumanitiesdata.metajnl.com/articles/572/files/6a7db75f2697f.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143812810","display_name":"Azal Alaswaad","orcid":"https://orcid.org/0000-0003-1636-0126","observed_orcids":["https://orcid.org/0000-0003-1636-0126"]},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Azal Alaswaad","raw_affiliation_strings":["Data Mining Lab, School of Computer Engineering, Artificial Intelligence & Digital Islamic Humanities Laboratory, Computer Research Center of Islamic Sciences (CRCIS), Iran University of Science & Technology, Tehran"],"raw_orcid":"https://orcid.org/0000-0003-1636-0126","affiliations":[{"raw_affiliation_string":"Data Mining Lab, School of Computer Engineering, Artificial Intelligence & Digital Islamic Humanities Laboratory, Computer Research Center of Islamic Sciences (CRCIS), Iran University of Science & Technology, Tehran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057087345","display_name":"Behrouz  Minaei Bidgoli","orcid":"https://orcid.org/0000-0002-9327-7345","observed_orcids":["https://orcid.org/0000-0002-9327-7345","https://orcid.org/0000-0001-5834-1041","https://orcid.org/0009-0007-5957-7145"]},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Behrouz Minaei-Bidgoli","raw_affiliation_strings":["Data Mining Lab, School of Computer Engineering, Artificial Intelligence & Digital Islamic Humanities Laboratory, Computer Research Center of Islamic Sciences (CRCIS), Iran University of Science & Technology, Tehran"],"raw_orcid":"https://orcid.org/0000-0002-9327-7345","affiliations":[{"raw_affiliation_string":"Data Mining Lab, School of Computer Engineering, Artificial Intelligence & Digital Islamic Humanities Laboratory, Computer Research Center of Islamic Sciences (CRCIS), Iran University of Science & Technology, Tehran","institution_ids":["https://openalex.org/I67009956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5057087345"],"corresponding_institution_ids":["https://openalex.org/I67009956"],"apc_list":{"value":300,"currency":"GBP","value_usd":367},"apc_paid":{"value":300,"currency":"GBP","value_usd":367},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","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":0.9976000189781189,"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":0.9976000189781189,"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":0.0013000000035390258,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.00019999999494757503,"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/classical-arabic","display_name":"Classical Arabic","score":0.9459999799728394},{"id":"https://openalex.org/keywords/arabic-morphological-analysis","display_name":"Arabic morphological analysis","score":0.7409999966621399},{"id":"https://openalex.org/keywords/complex-words","display_name":"complex words","score":0.546999990940094},{"id":"https://openalex.org/keywords/root-extraction","display_name":"root extraction","score":0.6460000276565552},{"id":"https://openalex.org/keywords/stemming","display_name":"stemming","score":0.9620000123977661},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.9269999861717224},{"id":"https://openalex.org/keywords/grammatical-case","display_name":"grammatical case","score":0.828000009059906},{"id":"https://openalex.org/keywords/quranic-text","display_name":"Quranic text","score":0.5950000286102295},{"id":"https://openalex.org/keywords/hadith","display_name":"hadith","score":0.7129999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802000045776367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.757099986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7028999924659729},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5835000276565552},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5633000135421753},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5334/johd.572","doi":"https://doi.org/10.5334/johd.572","is_oa":true,"landing_page_url":"https://doi.org/10.5334/johd.572","pdf_url":"https://openhumanitiesdata.metajnl.com/articles/572/files/6a7db75f2697f.pdf","source":{"id":"https://openalex.org/S4210240912","display_name":"Journal of Open Humanities Data","issn_l":"2059-481X","issn":["2059-481X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","erih-plus","jufo-1","norway-1","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Humanities Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7f9d787d467e4aabba6b9c6732fcf82e","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/7f9d787d467e4aabba6b9c6732fcf82e","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,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Open Humanities Data, Vol 12, Pp 110-110 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.5334/johd.572","doi":"https://doi.org/10.5334/johd.572","is_oa":true,"landing_page_url":"https://doi.org/10.5334/johd.572","pdf_url":"https://openhumanitiesdata.metajnl.com/articles/572/files/6a7db75f2697f.pdf","source":{"id":"https://openalex.org/S4210240912","display_name":"Journal of Open Humanities Data","issn_l":"2059-481X","issn":["2059-481X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","erih-plus","jufo-1","norway-1","poland-20","vabb-shw"],"host_organization":"https://openalex.org/P4310320511","host_organization_name":"Ubiquity Press","host_organization_lineage":["https://openalex.org/P4310320511"],"host_organization_lineage_names":["Ubiquity Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Humanities Data","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202378024.pdf","grobid_xml":"https://content.openalex.org/works/W7202378024.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W33221268","https://openalex.org/W1550053614","https://openalex.org/W2042777049","https://openalex.org/W2250816155","https://openalex.org/W4402959858"],"related_works":["https://openalex.org/W7128466208","https://openalex.org/W4384918672","https://openalex.org/W7054984437","https://openalex.org/W7140100493","https://openalex.org/W4211036676","https://openalex.org/W4405131073","https://openalex.org/W2897262086","https://openalex.org/W6925221519","https://openalex.org/W4414568683","https://openalex.org/W6939319248"],"abstract_inverted_index":{"The":[0,62],"Noor-Sharaye":[1],"dataset":[2],"is":[3,31],"a":[4],"morphologically":[5],"annotated":[6],"Classical":[7,19,60],"Arabic":[8,20,90],"corpus":[9],"containing":[10],"approximately":[11],"205,000":[12],"word":[13],"instances":[14],"extracted":[15],"from":[16],"17":[17],"different":[18],"books,":[21],"including":[22],"Quranic,":[23],"Fiqh,":[24],"Hadith,":[25],"and":[26,49,70,84],"historical":[27],"texts.":[28],"Each":[29],"token":[30],"enriched":[32],"with":[33],"detailed":[34],"linguistic":[35],"annotations":[36],"such":[37],"as":[38],"stem,":[39],"lemma,":[40],"root,":[41],"part-of-speech":[42],"tags,":[43],"segmentation,":[44],"grammatical":[45],"case,":[46],"gender,":[47],"number,":[48],"affix-level":[50],"features,":[51],"designed":[52],"to":[53],"capture":[54],"the":[55],"complex":[56],"morphological":[57,82],"structure":[58],"of":[59,86],"Arabic.":[61],"data":[63],"are":[64],"encoded":[65],"in":[66,89],"UTF-8":[67],"XLS,":[68],"XML,":[69],"JSON":[71],"formats":[72],"for":[73],"broad":[74],"compatibility.":[75],"This":[76],"resource":[77],"supports":[78],"stemming,":[79],"root":[80],"extraction,":[81],"analysis,":[83],"benchmarking":[85],"AI-based":[87],"models":[88],"Natural":[91],"Language":[92],"Processing.":[93]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-08-14T00:00:00"}
