{"id":"W2070529691","doi":"10.1109/ccece.2006.277770","title":"On Some Feature Selection Strategies for Spam Filter Design","year":2006,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Feature selection; Computer science; Artificial intelligence; Curse of dimensionality; Feature vector; Simulated annealing; Text categorization; Dimensionality reduction; Classifier (UML); Machine learning; Filter (signal processing); Pattern recognition (psychology); Support vector machine; Data mining; Feature extraction; Categorization","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":[0.0001191771,0.00007801236,0.0000564713,0.00006342086,0.0001197337,0.0003070632,0.0001633178,0.00006579405,0.00001129592],"category_scores_gemma":[0.000007366888,0.00006348707,0.00003792188,0.0001456914,0.000006546087,0.000613423,0.00001146142,0.00006870354,0.00002583149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002793685,"about_ca_system_score_gemma":0.00003174249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006021354,"about_ca_topic_score_gemma":0.00002793709,"domain_scores_codex":[0.9994629,0.0000236817,0.00006069732,0.000207325,0.0001014114,0.0001440017],"domain_scores_gemma":[0.999694,0.00009229928,0.00002673487,0.0001308886,0.00003781364,0.0000182768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003140247,0.00004758229,0.00002569443,0.000008081914,0.000006493834,8.44291e-7,0.00007240623,0.01116826,0.008096289,0.8096063,0.1665813,0.004355449],"study_design_scores_gemma":[0.0003847102,0.0006337469,0.001042455,0.000009565155,0.000005113719,0.00001162028,0.00001117253,0.2274642,0.06437446,0.6972107,0.008625613,0.0002266087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00480028,0.00001572304,0.9911633,0.0007595205,0.0004193326,0.0001639085,5.000866e-7,0.0002843285,0.002393081],"genre_scores_gemma":[0.8839505,9.216172e-7,0.1103516,0.0004797834,0.0003358544,0.00003709138,0.000002736164,0.000008286109,0.004833239],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8808118,"threshold_uncertainty_score":0.2961017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01955711205504025,"score_gpt":0.2310359724797079,"score_spread":0.2114788604246676,"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."}}