{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001060526,0.0005751966,0.0006432401,0.004070362,0.0005642158,0.001063736,0.0005178521,0.0008393715,0.001212751],"category_scores_gemma":[0.005408385,0.0001635048,0.0006345946,0.001358725,0.0005382313,0.001164679,0.0008738134,0.0006503707,0.001856681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005681487,"about_ca_system_score_gemma":0.0008119537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001071849,"about_ca_topic_score_gemma":0.002101457,"domain_scores_codex":[0.9985912,0.0005045383,0.0001768863,0.0002711497,0.000319113,0.0001370127],"domain_scores_gemma":[0.9963104,0.001421465,0.0006395639,0.000488896,0.001002949,0.000136699],"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":[0.001403151,0.001036234,0.05942423,0.0006167467,0.0002176437,0.000604213,0.0006957556,0.01626023,0.106983,0.005573806,0.01690913,0.7902758],"study_design_scores_gemma":[0.00006356365,0.0003700457,0.03736552,0.00008150634,0.0001364403,0.00111765,0.000427022,0.8993574,0.04535111,0.008266808,0.007394751,0.00006802846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7827237,0.001309963,0.2017756,0.0005393936,0.0003586926,0.0003856235,0.002524021,0.004242453,0.006140627],"genre_scores_gemma":[0.9516925,0.0002113916,0.04286177,0.0001030529,0.0001700336,0.0001276438,0.002520364,0.00008245751,0.002230698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004070362,"threshold_uncertainty_score":0.005608678,"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."}}