{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001601926,0.0000707861,0.00007451203,0.00004136456,0.0001360114,0.0003753848,0.0001732859,0.00005236179,0.00004765221],"category_scores_gemma":[0.00004295239,0.00005546677,0.00002076703,0.0001452682,0.00003020414,0.0007340124,0.0001154461,0.00009202537,0.00002759333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002474726,"about_ca_system_score_gemma":0.0000147519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001200879,"about_ca_topic_score_gemma":0.00004300315,"domain_scores_codex":[0.9993774,0.00003640916,0.00008802808,0.0002445747,0.0001099335,0.0001437058],"domain_scores_gemma":[0.9995199,0.00006483561,0.00002933586,0.0002805703,0.00004128822,0.00006403116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00000952796,0.0001135582,0.06665201,0.0001033646,0.00004223083,0.000007613863,0.002803319,0.000147217,0.1146292,0.04037078,0.01354022,0.761581],"study_design_scores_gemma":[0.0003388007,0.0001572963,0.5305276,0.00005850475,0.00001387527,0.0001983907,0.0002445181,0.3705335,0.04077718,0.05260353,0.003854539,0.0006922617],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7782711,0.0001084346,0.2132415,0.001048992,0.0003477157,0.0001455255,1.446462e-7,0.0002205353,0.00661603],"genre_scores_gemma":[0.9491464,0.000003081079,0.05017306,0.0002398417,0.00005774199,0.000003222959,1.191604e-7,0.000003213756,0.0003732961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7608888,"threshold_uncertainty_score":0.3619845,"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."}}