{"id":"W2049023511","doi":"10.1109/icdm.2013.131","title":"Classifying Spam Emails Using Text and Readability Features","year":2013,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Support vector machine; Artificial intelligence; Naive Bayes classifier; Header; Random forest; Machine learning; Readability; Bag-of-words model; Classifier (UML); 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":[0.001174694,0.0008913161,0.0008561107,0.007950076,0.0004719858,0.001028958,0.0004039297,0.0009545389,0.001179337],"category_scores_gemma":[0.006701939,0.0001416582,0.0004900876,0.002075192,0.0002765963,0.001647873,0.0004821442,0.0003919682,0.001364066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003513816,"about_ca_system_score_gemma":0.000310203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000968828,"about_ca_topic_score_gemma":0.001255609,"domain_scores_codex":[0.9989071,0.000215325,0.0001236969,0.0001526222,0.0004802102,0.0001209737],"domain_scores_gemma":[0.9938825,0.002255931,0.001270109,0.0004364156,0.001885022,0.000270056],"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":[0.001099206,0.001310761,0.2426354,0.0005740616,0.0002604267,0.0005814412,0.0004726051,0.01482489,0.05035232,0.001052693,0.0125202,0.6743161],"study_design_scores_gemma":[0.00007862636,0.001053803,0.3383529,0.000147797,0.0002924984,0.001579919,0.0006833056,0.5664331,0.07705244,0.004394293,0.00980023,0.0001309835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9006356,0.00115467,0.08548559,0.0002599725,0.0001466145,0.0003130198,0.00196803,0.003925317,0.006111185],"genre_scores_gemma":[0.9546387,0.0002470997,0.03859828,0.00008997674,0.0001989034,0.0001034724,0.003596093,0.00006984258,0.002457534],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007950076,"threshold_uncertainty_score":0.006212413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02317222889243716,"score_gpt":0.2407261376359102,"score_spread":0.217553908743473,"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."}}