{"id":"W4321379933","doi":"10.1177/20552076231158033","title":"Anti-vaccination attitude trends during the COVID-19 pandemic: A machine learning-based analysis of tweets","year":2023,"lang":"en","type":"article","venue":"Digital Health","topic":"Vaccine Coverage and Hesitancy","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Health and Medical Research Council; National Heart Foundation of Australia","keywords":"Vaccination; Misinformation; Pandemic; Coronavirus disease 2019 (COVID-19); Social media; Medicine; Family medicine; Demography; Computer science; Virology; Infectious disease (medical specialty); Sociology; World Wide Web; Computer security; Disease","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008266809,0.00008727403,0.0002655702,0.0004680043,0.0006726146,0.00008612958,0.0001930335,0.00004569895,0.000179138],"category_scores_gemma":[0.0004043371,0.00006878992,0.0001578517,0.00305384,0.00001626343,0.0002129277,0.00003351381,0.0001223674,0.00001821318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002377487,"about_ca_system_score_gemma":0.0003525681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002505431,"about_ca_topic_score_gemma":0.01126546,"domain_scores_codex":[0.9986856,0.0001627857,0.000279405,0.000197259,0.0003575751,0.0003173833],"domain_scores_gemma":[0.9991311,0.0002838247,0.0002002965,0.0001559936,0.00005211258,0.0001766067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001399083,0.00003687895,0.9842119,0.00004940508,0.00006870502,0.000003521387,0.003583787,0.004500228,0.000002315284,0.0002431188,0.0003541117,0.006932105],"study_design_scores_gemma":[0.0003485024,0.00005137153,0.9804061,0.000006773235,0.00003861081,3.773926e-7,0.0005933999,0.002288827,0.000002137552,0.00007024158,0.01610862,0.00008505665],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9880221,0.0002666772,0.0002168568,0.00870617,0.00005585379,0.0001251831,0.0000883495,0.0002248792,0.002293915],"genre_scores_gemma":[0.997038,0.0002074224,0.0000026181,0.000532205,0.00005609679,0.000006515069,0.0001729943,0.000008448841,0.001975714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01575451,"threshold_uncertainty_score":0.6286392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.058529492324616,"score_gpt":0.3879158816262634,"score_spread":0.3293863893016474,"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."}}