{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002637092,0.00008004094,0.0001480878,0.001304249,0.0004015821,0.0003684814,0.002315775,0.00002597767,0.00002931964],"category_scores_gemma":[0.001743842,0.00006878236,0.0001171539,0.003020915,0.0002176617,0.001692981,0.0002496269,0.0003785423,0.000007416232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000200404,"about_ca_system_score_gemma":0.0002108484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002792871,"about_ca_topic_score_gemma":0.000001066209,"domain_scores_codex":[0.9971961,0.00004585306,0.0002938477,0.0003475502,0.001788226,0.0003284241],"domain_scores_gemma":[0.9977427,0.0002908646,0.0001638946,0.0002155676,0.001376111,0.0002109109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003351779,0.0001095278,0.001740922,0.00001969924,0.0001725573,0.00001306441,0.001030845,0.03076658,0.4910747,0.02250808,0.0004418738,0.451787],"study_design_scores_gemma":[0.0002379015,0.001032763,0.004640558,0.00006271368,0.000009684355,0.00001207599,0.00005014503,0.7156164,0.2637731,0.00154164,0.01289789,0.0001251394],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3080793,0.00002767142,0.6801273,0.006328566,0.0007111955,0.0002223939,0.000009099837,0.00007351339,0.004421056],"genre_scores_gemma":[0.9541154,0.00009268051,0.04530556,0.0002368393,0.0001532446,0.00001434776,7.916867e-7,0.000004550982,0.00007659186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6848498,"threshold_uncertainty_score":0.4303325,"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."}}