{"id":"https://openalex.org/W4388821009","doi":"https://doi.org/10.1109/idsta58916.2023.10317860","title":"Arabic Web Page Classification with AraBert and Mixture vectorization Methods: Analysis Using K-NN, LSTM and Naive Bayes","display_name":"Arabic Web Page Classification with AraBert and Mixture vectorization Methods: Analysis Using K-NN, LSTM and Naive Bayes","publication_year":2023,"publication_date":"2023-10-24","ids":{"openalex":"https://openalex.org/W4388821009","doi":"https://doi.org/10.1109/idsta58916.2023.10317860"},"language":"en","primary_location":{"id":"doi:10.1109/idsta58916.2023.10317860","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/idsta58916.2023.10317860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Fourth International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087669051","display_name":"Abdelmounaim Kerkri","orcid":"https://orcid.org/0000-0002-5368-6355"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelmounaim Kerkri","raw_affiliation_strings":["National school of applied sciences,Laboratory of stochastic and deterministic modeling,Oujda,Morocco","Laboratory of stochastic and deterministic modeling, National school of applied sciences, Oujda, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National school of applied sciences,Laboratory of stochastic and deterministic modeling,Oujda,Morocco","institution_ids":[]},{"raw_affiliation_string":"Laboratory of stochastic and deterministic modeling, National school of applied sciences, Oujda, Morocco","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042766947","display_name":"M. Madani","orcid":"https://orcid.org/0000-0001-7548-1855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed Amine Madani","raw_affiliation_strings":["National school of applied sciences,Engineering Sciences Laboratory LSI,Oujda,Morocco","Engineering Sciences Laboratory LSI, National school of applied sciences, Oujda, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National school of applied sciences,Engineering Sciences Laboratory LSI,Oujda,Morocco","institution_ids":[]},{"raw_affiliation_string":"Engineering Sciences Laboratory LSI, National school of applied sciences, Oujda, Morocco","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093294144","display_name":"Hicham Ghouch","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hicham Ghouch","raw_affiliation_strings":["National school of applied sciences,Department of mathematics and applied mechanics,Oujda,Morocco","Department of mathematics and applied mechanics, National school of applied sciences, Oujda, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National school of applied sciences,Department of mathematics and applied mechanics,Oujda,Morocco","institution_ids":[]},{"raw_affiliation_string":"Department of mathematics and applied mechanics, National school of applied sciences, Oujda, Morocco","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093294145","display_name":"Karima El Majdoub","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karima El Majdoub","raw_affiliation_strings":["National school of applied sciences,Department of mathematics and applied mechanics,Oujda,Morocco","Department of mathematics and applied mechanics, National school of applied sciences, Oujda, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National school of applied sciences,Department of mathematics and applied mechanics,Oujda,Morocco","institution_ids":[]},{"raw_affiliation_string":"Department of mathematics and applied mechanics, National school of applied sciences, Oujda, Morocco","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57707821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9868000149726868,"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/computer-science","display_name":"Computer science","score":0.8183348178863525},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6816630363464355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6723278760910034},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5626754760742188},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5446251630783081},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5143519639968872},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41958826780319214},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.41395875811576843},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37180328369140625},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.2228393256664276},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16432645916938782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183348178863525},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6816630363464355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6723278760910034},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5626754760742188},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5446251630783081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5143519639968872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41958826780319214},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.41395875811576843},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37180328369140625},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2228393256664276},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16432645916938782},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/idsta58916.2023.10317860","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/idsta58916.2023.10317860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Fourth International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1967320885","https://openalex.org/W2064675550","https://openalex.org/W2896457183","https://openalex.org/W3008110149","https://openalex.org/W3129207397","https://openalex.org/W3134155512","https://openalex.org/W3153642904","https://openalex.org/W3168040464","https://openalex.org/W3173465197","https://openalex.org/W3175492893","https://openalex.org/W3176169354","https://openalex.org/W3177366285","https://openalex.org/W3183676217","https://openalex.org/W3203011138","https://openalex.org/W3203646744","https://openalex.org/W3205231356","https://openalex.org/W4385245566","https://openalex.org/W6793537811","https://openalex.org/W6794373130"],"related_works":["https://openalex.org/W4249048193","https://openalex.org/W3000360420","https://openalex.org/W1931440630","https://openalex.org/W2394466068","https://openalex.org/W1987683558","https://openalex.org/W3172144307","https://openalex.org/W2397288865","https://openalex.org/W3184247917","https://openalex.org/W2726838704","https://openalex.org/W4235657630"],"abstract_inverted_index":{"With":[0],"the":[1,5,11,13,104,125,139,162],"enormous":[2],"increase":[3],"in":[4,18,33,39,76],"volume":[6],"of":[7,15,30,41,69,114,124,143,164],"Arabic":[8,117],"content":[9,17],"on":[10],"Internet,":[12],"retrieval":[14],"this":[16,34,59,62],"an":[19],"accurate":[20],"and":[21,45,98,103,130,141],"rapid":[22],"manner":[23],"has":[24],"become":[25],"a":[26,55,66,112],"necessity.":[27],"Manual":[28],"categorization":[29],"web":[31,73,118],"pages":[32,74],"case":[35],"can":[36],"be":[37],"challenging":[38],"terms":[40],"optimizing":[42],"efficiency,":[43],"speed,":[44],"cost.":[46],"Therefore,":[47],"using":[48,93],"natural":[49],"language":[50],"processing":[51],"models":[52,71,156],"seems":[53],"like":[54],"suitable":[56],"choice":[57],"for":[58,72],"task.":[60],"In":[61],"paper,":[63],"we":[64,110,149],"present":[65],"comparative":[67,79],"study":[68,80],"classification":[70,159],"written":[75],"Arabic.":[77],"Our":[78],"includes":[81],"K-Nearest":[82],"Neighbor":[83],"(K-NN),":[84],"Long":[85],"Short-Term":[86],"Memory":[87],"model":[88,106],"(LSTM),":[89],"Naive":[90],"Bayes":[91],"(implemented":[92],"top":[94,96,99],"1%,":[95],"60%,":[97],"80%":[100],"mixture":[101,165],"methods),":[102],"transformer-based":[105],"AraBert.":[107],"For":[108],"training,":[109],"scraped":[111],"dataset":[113],"roughly":[115],"10,000":[116],"pages,":[119],"each":[120],"assigned":[121],"to":[122],"one":[123],"following":[126],"categories:":[127],"health,":[128],"economy,":[129],"politics.":[131],"Linguistic":[132],"preprocessing":[133],"was":[134],"carried":[135],"out,":[136],"followed":[137],"by":[138],"training":[140],"evaluation":[142],"our":[144],"models.":[145],"Using":[146],"performance":[147],"metrics,":[148,160],"conclude":[150],"that":[151],"AraBert":[152],"outperformed":[153],"all":[154,158],"other":[155],"across":[157],"despite":[161],"use":[163],"methods.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
