{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001340809,0.00004258128,0.00007100117,0.00007695608,0.0001250156,0.000169726,0.00006522077,0.00002755256,0.00001614949],"category_scores_gemma":[0.00003952215,0.00004008736,0.00003451265,0.000801536,0.000009511047,0.0002117635,0.00006296361,0.00006968136,0.000002707868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001519653,"about_ca_system_score_gemma":0.0000155559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001119313,"about_ca_topic_score_gemma":0.0002287088,"domain_scores_codex":[0.9995221,0.00004536179,0.00007810883,0.0001906056,0.00009252365,0.00007129017],"domain_scores_gemma":[0.9996758,0.0000343737,0.0000352611,0.0001643047,0.00005962904,0.00003070924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008641566,0.00006476751,0.4962221,0.00003521347,0.0006359813,0.00004087926,0.002893821,0.01333147,0.1145608,0.1325966,0.0001176586,0.239492],"study_design_scores_gemma":[0.00004870875,0.00000776975,0.01885107,0.000001530478,0.00004632573,0.00001169657,0.0000356016,0.9755396,0.004162265,0.0008342493,0.0004054711,0.000055761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2120439,0.00009886686,0.786843,0.0002203274,0.00007135709,0.00001111217,1.42294e-7,0.00006709235,0.0006441973],"genre_scores_gemma":[0.9198027,0.00001405818,0.0797484,0.00007866066,0.00002189223,4.356818e-7,0.00000385789,0.000002133147,0.000327871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9622081,"threshold_uncertainty_score":0.1636672,"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."}}