{"id":"W4205892035","doi":"10.3389/fpubh.2021.788074","title":"Detecting COVID-19-Related Fake News Using Feature Extraction","year":2022,"lang":"en","type":"article","venue":"Frontiers in Public Health","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Random forest; Preprocessor; Artificial intelligence; Lexical analysis; Social media; Feature selection; Classifier (UML); Data pre-processing; Feature extraction; Machine learning; Coronavirus disease 2019 (COVID-19); Sentiment analysis; Stop words; Information retrieval; Data mining; World Wide Web","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.004355628,0.00008998453,0.0001832636,0.0004757789,0.002261063,0.0001610887,0.000221142,0.00009833307,0.0006176505],"category_scores_gemma":[0.001621428,0.0001027458,0.00004507947,0.001480524,0.00006455284,0.000825475,0.00004820509,0.0005850563,0.000004024927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003804003,"about_ca_system_score_gemma":0.004502403,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007054145,"about_ca_topic_score_gemma":0.001213665,"domain_scores_codex":[0.9973728,0.0009124,0.0003459183,0.0001794782,0.000561407,0.0006280118],"domain_scores_gemma":[0.9988039,0.00005546692,0.0003097166,0.0001424986,0.0000312783,0.0006571448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002599033,0.0001102859,0.01548647,0.00005688722,0.00002404432,0.00000822707,0.3401036,0.002567396,0.000007444202,0.004904587,0.3338306,0.3028744],"study_design_scores_gemma":[0.0003615064,0.00002953778,0.001109998,0.000004103792,0.000001233008,0.000008764307,0.19428,0.005044755,4.097694e-7,0.0005012042,0.7985505,0.0001079608],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3545521,0.001530566,0.1524999,0.378206,0.01949961,0.00277374,0.00007339542,0.001037945,0.0898267],"genre_scores_gemma":[0.9758294,0.0001570953,0.006706096,0.01503561,0.0001461461,0.000008697525,0.00003235075,0.00001635846,0.002068231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6212773,"threshold_uncertainty_score":0.999558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0971768453981141,"score_gpt":0.3938123941448135,"score_spread":0.2966355487466994,"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."}}