{"id":"W2224734417","doi":"10.1007/s00521-015-2069-7","title":"Supervised classification of spam emails with natural language stylometry","year":2015,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Naive Bayes classifier; Random forest; Machine learning; Stylometry; Artificial intelligence; Support vector machine; Classifier (UML); Filter (signal processing); The Internet; Computational Science and Engineering; F1 score; World Wide Web; Natural language 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":[0.0001505696,0.00007521911,0.00009436688,0.00007606467,0.0001004812,0.00007300455,0.0002326212,0.00002876689,5.14316e-7],"category_scores_gemma":[0.00001606834,0.00006176793,0.00001786198,0.0004795532,0.0000417073,0.0001471829,0.00006277033,0.0001104179,0.000004516245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001290759,"about_ca_system_score_gemma":0.00002159168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003612526,"about_ca_topic_score_gemma":0.000004852306,"domain_scores_codex":[0.9993545,0.00003347942,0.0001302572,0.0002224173,0.0001516994,0.0001075959],"domain_scores_gemma":[0.9993899,0.00007358482,0.00008530629,0.0002824739,0.00009739376,0.00007136571],"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":[0.00004588956,0.0002453032,0.02581541,0.0001208853,0.00004628083,0.000004002043,0.006482225,0.001479559,0.05314409,0.04560015,0.001044329,0.8659719],"study_design_scores_gemma":[0.0009360114,0.0002624183,0.05981443,0.00003341807,0.00002160294,0.00008598058,0.0009067463,0.9289505,0.006456964,0.0006579056,0.001541054,0.0003329117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7779824,0.0003098774,0.2204017,0.0003913408,0.00007271391,0.0001686699,0.000002030851,0.0001632592,0.0005079646],"genre_scores_gemma":[0.9916892,0.000001565353,0.008121335,0.00006498537,0.00007730811,0.00000960621,0.000008294957,0.000003965884,0.00002374541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.927471,"threshold_uncertainty_score":0.2518823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0248393366903179,"score_gpt":0.2711033324943988,"score_spread":0.2462639958040809,"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."}}