{"id":"W3095418569","doi":"10.47392/irjash.2020.161","title":"Performance Analysis of Ml Techniques for Spam Filtering","year":2020,"lang":"en","type":"article","venue":"International Research Journal on Advanced Science Hub","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Forum spam; Spambot; The Internet; Bag-of-words model; Filter (signal processing); Volume (thermodynamics); Machine learning; Artificial intelligence; Data mining; World Wide Web; Spamming","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":[0.01258351,0.001625427,0.002016789,0.007436228,0.001237789,0.003572353,0.001542594,0.002251186,0.00585845],"category_scores_gemma":[0.06307527,0.0004937116,0.001275793,0.004922877,0.001033633,0.004228577,0.00191346,0.001759871,0.005272774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001925268,"about_ca_system_score_gemma":0.001627071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002314895,"about_ca_topic_score_gemma":0.00116878,"domain_scores_codex":[0.9844641,0.006525415,0.0008292955,0.001326252,0.00609709,0.0007578705],"domain_scores_gemma":[0.9291172,0.0551819,0.002673914,0.005788838,0.006747326,0.0004907909],"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":[0.001664032,0.000269714,0.01217798,0.001106097,0.0005977841,0.0001460964,0.0004048423,0.1859261,0.008566896,0.02095171,0.0159341,0.7522546],"study_design_scores_gemma":[0.00005198388,0.0005494189,0.005081628,0.000117923,0.0001395795,0.000353628,0.0001678254,0.9573738,0.01305741,0.01195406,0.01108689,0.0000658331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09008966,0.03039227,0.8362972,0.002589981,0.001031565,0.0002832614,0.00184214,0.01518564,0.02228827],"genre_scores_gemma":[0.7235878,0.007536229,0.2521315,0.0006092516,0.001483035,0.0003246768,0.004134155,0.001157178,0.009036151],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01258351,"threshold_uncertainty_score":0.06654876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1162640665412774,"score_gpt":0.4329391782060862,"score_spread":0.3166751116648088,"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."}}