{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005827343,0.0003930875,0.001097478,0.0004870987,0.001061691,0.0008462109,0.0006968783,0.0004104731,0.0003164141],"category_scores_gemma":[0.01303129,0.0003596453,0.0000744359,0.0006706061,0.000146745,0.001338864,0.0007523309,0.0006166862,0.000003213913],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002612981,"about_ca_system_score_gemma":0.006452496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008808211,"about_ca_topic_score_gemma":0.002777788,"domain_scores_codex":[0.9953743,0.0008594551,0.001379244,0.0006077102,0.0008686265,0.0009106313],"domain_scores_gemma":[0.9944023,0.000940913,0.001318733,0.0007417572,0.0007070525,0.001889231],"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":[0.0003213786,0.0003088621,0.1364938,0.007155615,0.0003431616,0.00001548761,0.3724754,0.000004025554,0.00001488414,0.01574454,0.3652329,0.10189],"study_design_scores_gemma":[0.004621973,0.0001528144,0.2177684,0.0002132961,0.000007397865,0.00002811156,0.08256695,0.0004805845,0.00000231923,0.0003102794,0.6928997,0.0009481827],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6975939,0.004134395,0.0008877585,0.2920026,0.0007540081,0.001597563,0.0009843826,0.0002133332,0.001832055],"genre_scores_gemma":[0.9765229,0.005627163,0.0002378917,0.01476285,0.0004992647,0.00001891439,0.002214657,0.00002159106,0.000094832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3276668,"threshold_uncertainty_score":0.9998856,"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."}}