{"id":"W3214812402","doi":"10.1109/swc50871.2021.00093","title":"Email Classification and Forensics Analysis using Machine Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Naive Bayes classifier; Support vector machine; Random forest; Machine learning; Benchmark (surveying); Electronic mail; Artificial intelligence; Statistical classification; Logistic regression; Server; Data mining; World Wide Web","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":[0.002209972,0.000894885,0.001054605,0.009251635,0.0009696947,0.001767826,0.001005271,0.001907164,0.001439746],"category_scores_gemma":[0.006039418,0.0002716947,0.001008994,0.003064738,0.00065957,0.001818955,0.0009650274,0.0009222676,0.00180577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007602992,"about_ca_system_score_gemma":0.000861496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001217307,"about_ca_topic_score_gemma":0.0009815684,"domain_scores_codex":[0.9976959,0.000645449,0.0002216391,0.0003408983,0.00085429,0.0002417828],"domain_scores_gemma":[0.9965571,0.001327438,0.0006550297,0.0004228818,0.0009337075,0.0001038028],"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":[0.0002964043,0.0006068437,0.02239504,0.0002694191,0.0001359153,0.0007489362,0.0002356677,0.06798897,0.01490053,0.004460223,0.006492258,0.8814697],"study_design_scores_gemma":[0.00001462798,0.0001314233,0.008941162,0.0000805305,0.00003637237,0.0006794197,0.000259343,0.9598101,0.01861834,0.007730143,0.003648472,0.00005004379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.191854,0.001977851,0.7915193,0.00138894,0.00028201,0.0003638612,0.0006663515,0.005443909,0.006503747],"genre_scores_gemma":[0.7612918,0.0008788671,0.2329219,0.0002067849,0.0002499145,0.0001716766,0.001047491,0.00006506508,0.003166595],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009251635,"threshold_uncertainty_score":0.01168764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03940705506960792,"score_gpt":0.2579181630718568,"score_spread":0.2185111080022489,"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."}}