{"id":"https://openalex.org/W4385337357","doi":"https://doi.org/10.1016/j.dib.2023.109460","title":"ANAD: Arabic news article dataset","display_name":"ANAD: Arabic news article dataset","publication_year":2023,"publication_date":"2023-07-28","ids":{"openalex":"https://openalex.org/W4385337357","doi":"https://doi.org/10.1016/j.dib.2023.109460","pmid":"https://pubmed.ncbi.nlm.nih.gov/37577410","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10415830"},"language":"en","primary_location":{"id":"doi:10.1016/j.dib.2023.109460","doi":"https://doi.org/10.1016/j.dib.2023.109460","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dib.2023.109460","pdf_url":null,"source":{"id":"https://openalex.org/S2481029507","display_name":"Data in Brief","issn_l":"2352-3409","issn":["2352-3409"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in Brief","raw_type":"journal-article"},"volume":null,"type":"data-paper","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.dib.2023.109460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007865239","display_name":"Mohammed Altamimi","orcid":"https://orcid.org/0000-0002-4170-6910","observed_orcids":["https://orcid.org/0000-0002-4170-6910"]},"institutions":[{"id":"https://openalex.org/I4210088963","display_name":"University of Ha'il","ror":"https://ror.org/013w98a82","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210088963"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Mohammed Altamimi","raw_affiliation_strings":["Department of Information and Computer Science, College of Computer Science and Engineering, University of Ha'il, Ha'il, 81481, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-4170-6910","affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, College of Computer Science and Engineering, University of Ha'il, Ha'il, 81481, Saudi Arabia","institution_ids":["https://openalex.org/I4210088963"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049203171","display_name":"Abdulaziz M. Alayba","orcid":"https://orcid.org/0000-0003-1075-1214","observed_orcids":["https://orcid.org/0000-0003-1075-1214"]},"institutions":[{"id":"https://openalex.org/I4210088963","display_name":"University of Ha'il","ror":"https://ror.org/013w98a82","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210088963"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Abdulaziz M. Alayba","raw_affiliation_strings":["Department of Information and Computer Science, College of Computer Science and Engineering, University of Ha'il, Ha'il, 81481, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-1075-1214","affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, College of Computer Science and Engineering, University of Ha'il, Ha'il, 81481, Saudi Arabia","institution_ids":["https://openalex.org/I4210088963"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007865239","https://openalex.org/A5049203171"],"corresponding_institution_ids":["https://openalex.org/I4210088963"],"apc_list":{"value":530,"currency":"USD","value_usd":530},"apc_paid":{"value":530,"currency":"USD","value_usd":530},"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":null,"first_page":"109460","last_page":"109460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4887999892234802,"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/T10028","display_name":"Topic Modeling","score":0.4887999892234802,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.4323999881744385,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.02800000086426735,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic language","score":0.6439999938011169},{"id":"https://openalex.org/keywords/news-corpus","display_name":"news corpus","score":0.6790000200271606},{"id":"https://openalex.org/keywords/topic-classification","display_name":"topic classification","score":0.800000011920929},{"id":"https://openalex.org/keywords/arabic-text-classification","display_name":"Arabic text classification","score":0.4300000071525574},{"id":"https://openalex.org/keywords/news-websites","display_name":"news websites","score":0.621999979019165}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7668349742889404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690576076507568},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6418008804321289},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.6137213706970215},{"id":"https://openalex.org/C512170562","wikidata":"https://www.wikidata.org/wiki/Q173799","display_name":"Entertainment","level":2,"score":0.5627545714378357},{"id":"https://openalex.org/C18918823","wikidata":"https://www.wikidata.org/wiki/Q49389","display_name":"Tourism","level":2,"score":0.5197317600250244},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4750896990299225},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4388953447341919},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4332687556743622},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3886570334434509},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3681436777114868},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2975855767726898},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1371041238307953},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11273318529129028},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.dib.2023.109460","doi":"https://doi.org/10.1016/j.dib.2023.109460","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dib.2023.109460","pdf_url":null,"source":{"id":"https://openalex.org/S2481029507","display_name":"Data in Brief","issn_l":"2352-3409","issn":["2352-3409"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in Brief","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10415830","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10415830","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10415830/pdf/main.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Brief","raw_type":"Text"},{"id":"pmid:37577410","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37577410","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in brief","raw_type":"News"},{"id":"pmh:oai:doaj.org/article:ab153bffb8964010a788149ca0dec8f0","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/ab153bffb8964010a788149ca0dec8f0","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data in Brief, Vol 50, Iss , Pp 109460- (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.dib.2023.109460","doi":"https://doi.org/10.1016/j.dib.2023.109460","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dib.2023.109460","pdf_url":null,"source":{"id":"https://openalex.org/S2481029507","display_name":"Data in Brief","issn_l":"2352-3409","issn":["2352-3409"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in Brief","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G4766845365","display_name":null,"funder_award_id":"BA-2207","funder_id":"https://openalex.org/F4320325395","funder_display_name":"University of Hail"}],"funders":[{"id":"https://openalex.org/F4320325395","display_name":"University of Hail","ror":"https://ror.org/013w98a82"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6906871038","https://openalex.org/W6906553099","https://openalex.org/W6906750878","https://openalex.org/W4402782462","https://openalex.org/W6887825496","https://openalex.org/W6906416547","https://openalex.org/W6887874129","https://openalex.org/W6944364824","https://openalex.org/W6906630085","https://openalex.org/W6943985642"],"abstract_inverted_index":{"In":[0,24],"this":[1,63],"paper,":[2],"we":[3],"present":[4],"a":[5,17,43],"modern":[6],"standard":[7],"Arabic":[8,12,28],"dataset":[9,64,83,103],"based":[10],"on":[11],"news":[13,29],"articles":[14,33,98],"collected":[15],"over":[16,31],"one-year":[18],"period":[19],"from":[20,26],"01/01/2021":[21],"to":[22,69,88,96,100],"12/31/2021.":[23],"total,":[25],"12":[27],"websites,":[30],"500,000":[32],"were":[34],"collected,":[35],"the":[36,75,82],"selection":[37],"of":[38,45,62,77],"which":[39],"was":[40],"driven":[41],"by":[42],"variety":[44],"topics,":[46],"including":[47],"sports,":[48],"economies,":[49],"local":[50],"news,":[51],"politics,":[52],"tech,":[53],"tourism,":[54],"entertainment,":[55],"cars,":[56],"health,":[57],"and":[58,71,81,92],"art.":[59],"The":[60,102],"development":[61],"will":[65],"enable":[66],"data":[67],"scientists":[68],"explore":[70],"experiment":[72],"effectively":[73],"in":[74],"field":[76],"natural":[78],"language":[79],"processing,":[80],"can":[84],"also":[85],"be":[86],"used":[87],"develop":[89],"machine":[90],"learning":[91,94],"deep":[93],"models":[95],"classify":[97],"according":[99],"topic.":[101],"is":[104],"available":[105],"for":[106],"download":[107],"at":[108],"https://github.com/alaybaa/ArabicArticlesDataset/tree/main.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2023-07-29T00:00:00"}
