{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006119619,0.001839479,0.001814186,0.003526442,0.0004803476,0.001077572,0.001017416,0.001197401,0.0007063036],"category_scores_gemma":[0.007561194,0.0003135304,0.001274706,0.001804984,0.0002584555,0.001947618,0.0007559609,0.00152645,0.0006997815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007957621,"about_ca_system_score_gemma":0.0007696152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005587906,"about_ca_topic_score_gemma":0.004201865,"domain_scores_codex":[0.9978808,0.0009490227,0.0001532783,0.0003744392,0.0005073013,0.0001351225],"domain_scores_gemma":[0.994052,0.003808941,0.000333938,0.0004809945,0.00116602,0.0001580362],"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":[0.000844571,0.0005282877,0.02131611,0.0003785496,0.0008052622,0.0001116073,0.0002644623,0.3271838,0.002366417,0.001863078,0.005988816,0.6383489],"study_design_scores_gemma":[0.00001073799,0.0001826479,0.002887367,0.00003771774,0.00009035108,0.00003980245,0.00005490553,0.9932652,0.001154461,0.001140068,0.001119992,0.00001669904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.505766,0.02588591,0.4501166,0.002584055,0.0008508839,0.0002942262,0.001143352,0.00524898,0.008109869],"genre_scores_gemma":[0.8694177,0.005681593,0.1185495,0.0003763213,0.0005151866,0.0001710259,0.001786596,0.0001777649,0.003324301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006119619,"threshold_uncertainty_score":0.03236407,"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."}}