{"id":"W4414582179","doi":"10.61356/j.mawa.2025.8596","title":"Ensemble Learning Approaches for SMS Spam Detection: A Comparative Study of Text Classification Models","year":2025,"lang":"en","type":"article","venue":"Multicriteria Algorithms with Applications","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Preprocessor; Support vector machine; Pipeline (software); Normalization (sociology); Logistic regression; Ensemble learning; Relevance (law); Class (philosophy); Data pre-processing","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":[],"consensus_categories":[],"category_scores_codex":[0.0002502402,0.0001779434,0.0002595178,0.0002278664,0.0004439397,0.0001531851,0.0004398684,0.00007355618,0.00000107344],"category_scores_gemma":[0.00001365177,0.0001648445,0.00004905939,0.0009171781,0.00006048142,0.000389678,0.00007400324,0.0001550187,0.000003865802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006709551,"about_ca_system_score_gemma":0.00005786509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009356775,"about_ca_topic_score_gemma":0.00008148173,"domain_scores_codex":[0.9986223,0.00009258174,0.0003465246,0.0005614207,0.000179214,0.000197931],"domain_scores_gemma":[0.998661,0.0002051929,0.0001973189,0.0005745352,0.0003089954,0.00005289426],"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":[0.0004277383,0.005292497,0.001120177,0.0003447184,0.0006072892,9.962823e-7,0.03471396,0.09779233,0.04328042,0.07080948,0.0001398,0.7454706],"study_design_scores_gemma":[0.00111283,0.0004367297,0.001639375,0.00001923193,0.00005418427,0.000003271753,0.003021791,0.9816477,0.008410168,0.00235589,0.001121981,0.0001769015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03042944,0.00004560611,0.9660515,0.0001387717,0.0001056245,0.002436356,0.000004832432,0.0001997688,0.0005881668],"genre_scores_gemma":[0.8760659,0.000002280625,0.1198444,0.00001359201,0.00004786451,0.003834566,0.00001158133,0.00001036472,0.0001695103],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8838553,"threshold_uncertainty_score":0.6722165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1024160063710814,"score_gpt":0.3100702059987787,"score_spread":0.2076541996276973,"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."}}