{"id":"W1505739892","doi":"10.1109/ijcnn.2005.1556308","title":"Comparison of a SOM based sequence analysis system and naive Bayesian classifier for spam filtering","year":2006,"lang":"en","type":"article","venue":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Naive Bayes classifier; Classifier (UML); Artificial intelligence; Bayesian probability; Sequence (biology); Machine learning; Filter (signal processing); Data mining; Pattern recognition (psychology); Bag-of-words model; Support vector machine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003827864,0.000282677,0.0004591024,0.0004324971,0.0001499022,0.0004497997,0.0005879751,0.0001352368,0.00003302274],"category_scores_gemma":[0.00004000281,0.000271121,0.0001884812,0.0003680428,0.00008174784,0.0005463281,0.00006966801,0.000249604,0.000002782328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001725456,"about_ca_system_score_gemma":0.00004498406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009293525,"about_ca_topic_score_gemma":0.00006928672,"domain_scores_codex":[0.9977999,0.00002510609,0.0006325532,0.0006376031,0.0004828926,0.0004219841],"domain_scores_gemma":[0.9985819,0.0001211584,0.0005412865,0.0001749755,0.0004556817,0.00012497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007564102,0.0008332203,0.06430711,0.0005619049,0.00116324,0.00002517687,0.000662305,0.3843437,0.07068372,0.4352305,0.02157743,0.01985528],"study_design_scores_gemma":[0.0003445383,0.0001228654,0.002132227,0.0001837063,0.00006285905,0.00000820006,0.00004994795,0.9888172,0.007320363,0.0004174832,0.0002749116,0.0002657167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09025075,0.00005294972,0.9038828,0.001781503,0.001107123,0.0004453258,0.00003309328,0.0002302232,0.00221625],"genre_scores_gemma":[0.9891623,0.000008874366,0.0100221,0.0001417394,0.0004134641,0.00006856333,0.00001908386,0.00001583495,0.000148073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8989115,"threshold_uncertainty_score":0.9999741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07117352416471609,"score_gpt":0.3053486853818946,"score_spread":0.2341751612171785,"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."}}