{"id":"W3141725779","doi":"10.18178/ijmlc.2021.11.1.1017","title":"An Ensemble Framework for Spam Detection on Social Media Platforms","year":2021,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Computing","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University","keywords":"Computer science; Popularity; Social media; Spambot; Field (mathematics); Domain (mathematical analysis); Filter (signal processing); Data science; Machine learning; Artificial intelligence; The Internet; World Wide Web; Spamming","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005428725,0.00008316942,0.0001248546,0.0001291769,0.0002401465,0.0002889805,0.0002723783,0.00006541608,0.000003883482],"category_scores_gemma":[0.0005806112,0.00007588742,0.00008165785,0.0001000344,0.00001147567,0.0002582238,0.00005905968,0.0004596193,0.000001235369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004102976,"about_ca_system_score_gemma":0.00003365573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005131777,"about_ca_topic_score_gemma":0.000006380503,"domain_scores_codex":[0.999109,0.00005397627,0.0002401026,0.0001556578,0.0003281572,0.0001131072],"domain_scores_gemma":[0.9986896,0.0005708768,0.0002915806,0.00005159036,0.0003413766,0.00005499734],"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":[0.00009912209,0.00006415277,0.001390511,0.000005930006,0.00006626152,0.00003865835,0.002273052,0.00467479,0.00281972,0.01610564,0.00001527267,0.9724469],"study_design_scores_gemma":[0.001500581,0.0007252389,0.01084308,0.0002247566,0.00002291649,0.001082703,0.0004255431,0.8857167,0.0222327,0.07319979,0.00372258,0.0003033681],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3505753,0.00006864259,0.6474015,0.0004181917,0.001454401,0.00001269147,4.905946e-7,0.00002862061,0.00004021069],"genre_scores_gemma":[0.9639881,0.00001635927,0.03428281,0.0001610897,0.001532939,3.459528e-7,0.00000264459,0.000007713563,0.000007976719],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9721435,"threshold_uncertainty_score":0.3094599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02080755633202437,"score_gpt":0.3065384558866426,"score_spread":0.2857308995546182,"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."}}