{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003470212,0.0006521085,0.001140581,0.001385117,0.0005878892,0.00122148,0.0009909732,0.001359323,0.002096814],"category_scores_gemma":[0.008236418,0.0004351879,0.000544233,0.0009417192,0.0004126512,0.001917367,0.0006173642,0.0005550301,0.001488406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009960078,"about_ca_system_score_gemma":0.001468923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007655645,"about_ca_topic_score_gemma":0.008494969,"domain_scores_codex":[0.9978613,0.0006601532,0.0001572684,0.0003431961,0.0008471339,0.000130886],"domain_scores_gemma":[0.9948036,0.001933152,0.0002080294,0.0003747073,0.002501525,0.0001789306],"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":[0.002928421,0.0006594879,0.005987565,0.0002810607,0.0002801837,0.0001076518,0.0001302789,0.05036192,0.03579994,0.002527825,0.003626938,0.8973087],"study_design_scores_gemma":[0.0001080152,0.0005128635,0.003114803,0.00001911772,0.00009108559,0.000178587,0.00005617526,0.9705144,0.02148708,0.001812173,0.002060815,0.00004489185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1517759,0.001011526,0.8372851,0.0003549132,0.0002064579,0.0002448566,0.0001951683,0.005197261,0.003728769],"genre_scores_gemma":[0.5260023,0.0003881237,0.4679897,0.0002943958,0.000131292,0.0001874394,0.000508363,0.0001292435,0.004369087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007655645,"threshold_uncertainty_score":0.01835245,"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."}}