{"id":"W4415222211","doi":"10.2196/64723","title":"Evaluating Large Language Models for Sentiment Analysis and Hesitancy Analysis on Vaccine Posts From Social Media: Qualitative Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Vaccine Coverage and Hesitancy","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Qualitative research; Adaptation (eye); Qualitative analysis; Sentiment analysis; Focus (optics); Annotation; Focus group; Risk communication","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":[0.01761494,0.0004633757,0.0003154986,0.00103595,0.000892972,0.001324034,0.001244764,0.0007841839,0.001915175],"category_scores_gemma":[0.05687142,0.000269585,0.0005482814,0.0008637918,0.001399296,0.002634763,0.001417393,0.001005908,0.0004900456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003434285,"about_ca_system_score_gemma":0.001676116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01157673,"about_ca_topic_score_gemma":0.01500914,"domain_scores_codex":[0.9939813,0.004563496,0.0001762169,0.0003623661,0.0007023558,0.0002143235],"domain_scores_gemma":[0.9389392,0.05349223,0.00142713,0.001064009,0.004627284,0.0004502667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0007378521,0.002538186,0.402092,0.001826626,0.0002399876,0.002359742,0.2913421,0.02572159,0.009359501,0.01073091,0.01102352,0.242028],"study_design_scores_gemma":[0.0001446822,0.001457355,0.1061896,0.0009113707,0.0002979665,0.001088353,0.391338,0.4502584,0.01441474,0.009980882,0.02372887,0.0001896648],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9870405,0.0001207299,0.00915488,0.0007951384,0.00001340272,0.0002954975,0.0003959769,0.00004298436,0.002140995],"genre_scores_gemma":[0.9869546,0.0001198788,0.01121163,0.0001289288,0.000008728414,0.0004011647,0.0004224931,0.00003343595,0.0007191066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01761494,"threshold_uncertainty_score":0.09315783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1035723620820989,"score_gpt":0.5366815024176405,"score_spread":0.4331091403355416,"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."}}