{"id":"W7124153997","doi":"10.1109/codit66093.2025.11321615","title":"A BERT Deep Learning Model for Arabic Spam Detection","year":2025,"lang":"","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton; Université Laval","funders":"","keywords":"Lexical analysis; Deep learning; Arabic; Encoder; Phishing; Inference; Autoencoder; n-gram","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006856027,0.0002792799,0.0002686165,0.0003669015,0.0009351389,0.0006347215,0.0005527241,0.0002741108,0.00002650388],"category_scores_gemma":[0.0002909763,0.0002954399,0.000251977,0.0009843557,0.00004795634,0.000773449,0.0002090599,0.0004467013,0.00004934366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001936205,"about_ca_system_score_gemma":0.0001464783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001655741,"about_ca_topic_score_gemma":0.0004586566,"domain_scores_codex":[0.9978644,0.00009751155,0.000426919,0.0008407473,0.0002432964,0.0005271381],"domain_scores_gemma":[0.9987715,0.0002294121,0.0001417433,0.0004915553,0.0002596355,0.0001061193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009452912,0.00007322076,0.0001674094,0.0001046305,0.00005978654,6.612e-7,0.001100807,0.1708821,0.003420161,0.009693844,0.0001856661,0.8142172],"study_design_scores_gemma":[0.0006203935,0.0002694344,0.0002700191,0.00006329219,0.00005843789,0.000005635643,0.00004618223,0.9661052,0.01075541,0.01798727,0.0035239,0.0002948366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007774493,0.0004148669,0.9808536,0.0008585584,0.002993428,0.0005571863,5.72718e-7,0.0003708018,0.006176454],"genre_scores_gemma":[0.9518308,0.00006438683,0.02153693,0.0004921364,0.0001846136,0.00009983155,0.000001252997,0.00001717105,0.0257729],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9593167,"threshold_uncertainty_score":0.9999498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01608217729700309,"score_gpt":0.2519152551136856,"score_spread":0.2358330778166825,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}