{"id":"W4415707567","doi":"10.1109/tcss.2025.3608636","title":"Detecting the Presence of COVID-19 Vaccination Hesitancy From South African Twitter Data Using Machine Learning","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Computational Social Systems","topic":"Vaccine Coverage and Hesitancy","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Social media; Latent Dirichlet allocation; Support vector machine; Preprocessor; Microblogging; Sentiment analysis; Topic model; Data pre-processing","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001597133,0.000343872,0.0005634172,0.0002861562,0.005220895,0.000361838,0.001031792,0.0002787054,0.0002698057],"category_scores_gemma":[0.0002545661,0.0003312752,0.0002425492,0.001647645,0.00009054884,0.0005139026,0.00002278807,0.0007363094,0.00001452453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007421116,"about_ca_system_score_gemma":0.001276802,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02236994,"about_ca_topic_score_gemma":0.001360881,"domain_scores_codex":[0.9946806,0.00193918,0.001056936,0.0007797569,0.001091906,0.0004515627],"domain_scores_gemma":[0.9953769,0.002856086,0.0008431328,0.0003467663,0.0004287034,0.0001484509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000238345,0.0002838128,0.003406937,0.0002912981,0.0006728768,0.000005558237,0.07510356,0.9127676,0.0001651492,0.0008439069,0.0003597169,0.00586126],"study_design_scores_gemma":[0.00147091,0.00009082841,0.003276621,0.0003066777,0.0006365729,0.000003044898,0.04816711,0.940605,0.00008723472,0.002768372,0.002060225,0.0005273581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07109982,0.001159584,0.920131,0.003337791,0.002215023,0.001015599,0.0005103875,0.00009277399,0.0004380566],"genre_scores_gemma":[0.9982301,0.00004389176,0.0002662653,0.0002090527,0.0005823821,0.00003005482,0.00003976481,0.00002900015,0.0005694854],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9271303,"threshold_uncertainty_score":0.9999139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07998172010588879,"score_gpt":0.3462341620271521,"score_spread":0.2662524419212633,"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."}}