{"id":"W3047131763","doi":"10.2196/20794","title":"Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Pharmaceutical Quality and Counterfeiting","field":"Medicine","cited_by":120,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Social media; Counterfeit; Internet privacy; Public health; Sentiment analysis; Pandemic; Advertising; The Internet; Computer science; Public health surveillance; Product (mathematics); World Wide Web; Coronavirus disease 2019 (COVID-19); Business; Medicine; Artificial intelligence; Political science; Disease; Infectious disease (medical specialty)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001444143,0.0006244399,0.0004640336,0.002081341,0.0006576038,0.001018203,0.0005440478,0.0008652454,0.0009023104],"category_scores_gemma":[0.003878783,0.0002175173,0.0008115082,0.001093153,0.0005002391,0.001743731,0.0008773216,0.001068613,0.0005956165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006571015,"about_ca_system_score_gemma":0.0005316315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00706534,"about_ca_topic_score_gemma":0.01177161,"domain_scores_codex":[0.9989607,0.0003812118,0.00008000033,0.0001725226,0.0002456682,0.000159872],"domain_scores_gemma":[0.9973502,0.001466217,0.0002952507,0.0002878067,0.0003823802,0.0002182045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00167374,0.004778104,0.6467214,0.0006925359,0.0005003431,0.002327713,0.00275858,0.02182032,0.01331942,0.003685388,0.02925393,0.2724686],"study_design_scores_gemma":[0.00008800726,0.0009368106,0.4560277,0.0001342001,0.0002203671,0.0008769471,0.007990286,0.5060098,0.008659493,0.005414529,0.0134964,0.000145463],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834477,0.0005114693,0.006072681,0.002333044,0.0001330295,0.0001746603,0.003513559,0.0002783854,0.003535426],"genre_scores_gemma":[0.9839851,0.0002502888,0.009039509,0.0004455736,0.0001196193,0.0001393885,0.004721939,0.00003536233,0.001263212],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00706534,"threshold_uncertainty_score":0.0140484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1509587901491284,"score_gpt":0.4118671109403815,"score_spread":0.260908320791253,"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."}}