{"id":"W3003451442","doi":"10.2196/14952","title":"Classification of Health-Related Social Media Posts: Evaluation of Post Content–Classifier Models and Analysis of User Demographics","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Social media; Demographics; Content analysis; Internet privacy; Psychology; Medical education; World Wide Web; Computer science; Medicine; Sociology","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":[0.007742232,0.001515096,0.00147246,0.003199232,0.0006533453,0.001436565,0.001014265,0.001875727,0.00109669],"category_scores_gemma":[0.0139496,0.0002593308,0.001015144,0.001219078,0.0004010895,0.002010492,0.0008546021,0.001211559,0.001263687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009579326,"about_ca_system_score_gemma":0.0008532839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0063878,"about_ca_topic_score_gemma":0.005468722,"domain_scores_codex":[0.996646,0.001162384,0.0004082152,0.0007000522,0.0006739557,0.0004093731],"domain_scores_gemma":[0.981883,0.01212053,0.001144865,0.0008326407,0.003239787,0.0007791441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003406551,0.002764573,0.510268,0.000422238,0.0005773957,0.000289935,0.0008648885,0.03674407,0.007302513,0.0003804524,0.009642099,0.4273373],"study_design_scores_gemma":[0.00005845656,0.0008665232,0.06463171,0.00006217329,0.0001404818,0.0001935766,0.0004974596,0.9267259,0.005379988,0.0004532849,0.0009460015,0.00004446288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9622147,0.0007661795,0.0300904,0.0006206298,0.0003259407,0.0004456235,0.001938531,0.00138418,0.002213824],"genre_scores_gemma":[0.9735777,0.0001715523,0.02239649,0.0001246033,0.0001528337,0.0001641691,0.002164425,0.00003322009,0.001214974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007742232,"threshold_uncertainty_score":0.04094529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3549741211194267,"score_gpt":0.4229015895201598,"score_spread":0.06792746840073305,"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."}}