{"id":"W3161900227","doi":"10.2196/30642","title":"COVID-19 Vaccine Hesitancy on Social Media: Building a Public Twitter Data Set of Antivaccine Content, Vaccine Misinformation, and Conspiracies","year":2021,"lang":"en","type":"preprint","venue":"JMIR Public Health and Surveillance","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Annenberg Foundation","keywords":"Misinformation; Social media; Coronavirus disease 2019 (COVID-19); Pandemic; Internet privacy; Computer science; Political science; World Wide Web; Medicine; Computer security","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":[0.001037925,0.0007820395,0.0004832591,0.005867886,0.001263091,0.001356643,0.0008584583,0.001464279,0.002319344],"category_scores_gemma":[0.005136704,0.0002910674,0.000646768,0.004050164,0.0008546701,0.002063957,0.003032406,0.001194812,0.003650134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007621635,"about_ca_system_score_gemma":0.0009152605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01379544,"about_ca_topic_score_gemma":0.02380608,"domain_scores_codex":[0.9985668,0.000373065,0.0001572663,0.0003283411,0.0003421133,0.0002324471],"domain_scores_gemma":[0.9962457,0.001324864,0.0006509012,0.0006288604,0.0006838556,0.0004657938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001123325,0.002394469,0.5151817,0.003743621,0.0003114917,0.006445456,0.02094855,0.009263731,0.02297022,0.006658596,0.2352585,0.1757005],"study_design_scores_gemma":[0.0002277391,0.000638695,0.6192686,0.0005071199,0.0002199595,0.002027957,0.02512848,0.06235677,0.013405,0.004577125,0.2713067,0.0003359048],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.6733235,0.0004576442,0.006334563,0.001703179,0.0002031618,0.001758433,0.305835,0.001444926,0.008939583],"genre_scores_gemma":[0.4844231,0.0005564246,0.03417334,0.0007551939,0.0003176689,0.004518935,0.4673203,0.0003418473,0.007593215],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01379544,"threshold_uncertainty_score":0.0274303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2746321796056673,"score_gpt":0.4208009851453553,"score_spread":0.146168805539688,"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."}}