{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007736647,0.0005202167,0.000335571,0.002664305,0.0004891952,0.0006029656,0.0002441893,0.0006013282,0.001043934],"category_scores_gemma":[0.003201901,0.0001465243,0.000303326,0.001507591,0.0002780758,0.0009377782,0.0005290065,0.0005344946,0.0009226261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004681007,"about_ca_system_score_gemma":0.0003616137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00637557,"about_ca_topic_score_gemma":0.01088034,"domain_scores_codex":[0.9996178,0.0001019967,0.00005139244,0.00007369489,0.0000887953,0.00006635522],"domain_scores_gemma":[0.9983315,0.0008689549,0.0003227457,0.0001094088,0.000276958,0.00009041356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001398269,0.0003994438,0.6274062,0.001741695,0.000244816,0.002895916,0.006063532,0.01241119,0.0762111,0.001862393,0.02235023,0.2470151],"study_design_scores_gemma":[0.00003357402,0.0003468796,0.7496563,0.0003298245,0.0001109649,0.0009057001,0.01020219,0.1734303,0.02750161,0.001755478,0.03562813,0.00009891905],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9807789,0.0005315421,0.004615414,0.0007735802,0.0001226583,0.0001424167,0.009170723,0.0003085008,0.003556342],"genre_scores_gemma":[0.9801162,0.0003778578,0.007377914,0.0001000462,0.00009253933,0.0001334801,0.01026547,0.00002429884,0.001512115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00637557,"threshold_uncertainty_score":0.01267695,"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."}}