{"id":"https://openalex.org/W7124153997","doi":"https://doi.org/10.1109/codit66093.2025.11321615","title":"A BERT Deep Learning Model for Arabic Spam Detection","display_name":"A BERT Deep Learning Model for Arabic Spam Detection","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W7124153997","doi":"https://doi.org/10.1109/codit66093.2025.11321615"},"language":null,"primary_location":{"id":"doi:10.1109/codit66093.2025.11321615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit66093.2025.11321615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 11th International Conference on Control, Decision and Information Technologies (CoDIT)","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/A5122992317","display_name":"Hadir Driss","orcid":null},"institutions":[{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Hadir Driss","raw_affiliation_strings":["University of Tunis El-Manar,High Institute of Computer Science,Tunis,Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tunis El-Manar,High Institute of Computer Science,Tunis,Tunisia","institution_ids":["https://openalex.org/I63596082"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037252341","display_name":"Jaouhar Fattahi","orcid":"https://orcid.org/0000-0002-3905-9099"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jaouhar Fattahi","raw_affiliation_strings":["Laval University,Department of Computer Science and Software Engineering,Quebec,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laval University,Department of Computer Science and Software Engineering,Quebec,Canada","institution_ids":["https://openalex.org/I43406934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103270186","display_name":"Mohamed Mejri","orcid":"https://orcid.org/0000-0002-0455-7880"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohamed Mejri","raw_affiliation_strings":["Laval University,Department of Computer Science and Software Engineering,Quebec,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laval University,Department of Computer Science and Software Engineering,Quebec,Canada","institution_ids":["https://openalex.org/I43406934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123038278","display_name":"Sahbi Bahroun","orcid":null},"institutions":[{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Sahbi Bahroun","raw_affiliation_strings":["University of Tunis El-Manar,High Institute of Computer Science,Tunis,Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tunis El-Manar,High Institute of Computer Science,Tunis,Tunisia","institution_ids":["https://openalex.org/I63596082"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068087634","display_name":"Ridha Ghayoula","orcid":"https://orcid.org/0000-0002-3893-6977"},"institutions":[{"id":"https://openalex.org/I154799132","display_name":"Universit\u00e9 de Moncton","ror":"https://ror.org/029tnqt29","country_code":"CA","type":"education","lineage":["https://openalex.org/I154799132"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ridha Ghayoula","raw_affiliation_strings":["University of Moncton,Faculty of Engineering,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Moncton,Faculty of Engineering,Canada","institution_ids":["https://openalex.org/I154799132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75565916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1648","last_page":"1653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.973800003528595,"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"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.973800003528595,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0035000001080334187,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.002099999925121665,"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/lexical-analysis","display_name":"Lexical analysis","score":0.7268999814987183},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6726999878883362},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6068000197410583},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42820000648498535},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.4268999993801117},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.35120001435279846},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.33959999680519104},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.32839998602867126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371999859809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7803999781608582},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7268999814987183},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6726999878883362},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6068000197410583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44119998812675476},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.4268999993801117},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.32839998602867126},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.3262999951839447},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codit66093.2025.11321615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit66093.2025.11321615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 11th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7462252378463745,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2963626623","https://openalex.org/W3201648943","https://openalex.org/W4213311630","https://openalex.org/W4280636869","https://openalex.org/W4296047714","https://openalex.org/W4316660865","https://openalex.org/W4318320799","https://openalex.org/W4381738078","https://openalex.org/W4402690141","https://openalex.org/W4403534815"],"related_works":[],"abstract_inverted_index":{"Spam":[0],"messages":[1],"pose":[2],"a":[3,55,88],"significant":[4],"cybersecurity":[5],"threat,":[6],"leading":[7],"to":[8,28,71],"phishing":[9],"attacks,":[10],"fraud,":[11],"and":[12,23,32,82,94,111,133],"privacy":[13],"breaches.":[14],"Traditional":[15],"spam":[16,36,45,93,125],"detection":[17,46,135],"methods,":[18],"such":[19],"as":[20],"rule-based":[21],"filtering":[22],"statistical":[24],"models,":[25],"often":[26],"fail":[27],"capture":[29],"the":[30,72,84,118,128],"evolving":[31],"complex":[33],"nature":[34],"of":[35,91,120],"messages.":[37,96],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"an":[43],"Arabic":[44,73,77,92,124],"model":[47,86,102],"leveraging":[48],"BERT":[49],"(Bidirectional":[50],"Encoder":[51],"Representations":[52],"from":[53],"Transformers),":[54],"deep":[56,112],"learning-based":[57],"NLP":[58],"model.":[59],"Our":[60],"approach":[61],"enhances":[62],"classification":[63],"accuracy":[64,105],"by":[65],"utilizing":[66],"contextual":[67],"text":[68,78],"representations":[69],"specific":[70],"language.":[74],"We":[75],"preprocess":[76],"using":[79],"AraBERT":[80],"tokenization":[81],"fine-tune":[83],"BERT-based":[85],"on":[87],"balanced":[89],"dataset":[90],"ham":[95],"Experimental":[97],"results":[98],"demonstrate":[99],"that":[100],"our":[101],"achieves":[103],"high":[104],"(98%),":[106],"outperforming":[107],"traditional":[108],"machine":[109],"learning":[110,113],"approaches.":[114],"This":[115],"research":[116],"highlights":[117],"potential":[119],"transformer-based":[121],"models":[122],"in":[123],"filtering,":[126],"paving":[127],"way":[129],"for":[130],"more":[131],"efficient":[132],"robust":[134],"systems.":[136]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-15T00:00:00"}