{"id":"W4407396206","doi":"10.2196/62703","title":"Identifying Misinformation About Unproven Cancer Treatments on Social Media Using User-Friendly Linguistic Characteristics: Content Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Infodemiology","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Misinformation; Social media; Computer science; Viewpoints; Psychology; Artificial intelligence; Natural language processing; Applied psychology; World Wide Web; Computer security","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000677602,0.0001781129,0.0004574129,0.0004778799,0.0006959053,0.0001322703,0.0002364348,0.0002586547,0.0002189423],"category_scores_gemma":[0.001719237,0.0001650408,0.000178801,0.000715788,0.0001910769,0.0003223733,0.00005645822,0.0001934176,0.00004222911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006007101,"about_ca_system_score_gemma":0.000356177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0015406,"about_ca_topic_score_gemma":0.0007459922,"domain_scores_codex":[0.9981568,0.0002135212,0.0007211734,0.0001857056,0.0002807147,0.0004420629],"domain_scores_gemma":[0.9986094,0.000316042,0.0005061595,0.0001704853,0.0002768012,0.0001210835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0006007189,0.0003523117,0.166071,0.0002483261,0.002782158,0.00001011798,0.4762936,0.001759399,0.000395184,0.2295304,0.006533836,0.1154231],"study_design_scores_gemma":[0.001249025,0.00004327506,0.9590484,0.0001363873,0.0007538035,4.575176e-7,0.01118361,0.009585576,0.00006932936,0.0007745844,0.01674783,0.0004076849],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9817781,0.00004488668,0.003020332,0.0005598409,0.001085083,0.0004248818,0.00007517842,0.0001032581,0.01290838],"genre_scores_gemma":[0.9971188,0.0001144677,0.000300159,0.001428418,0.0002718102,0.00002961695,0.00009520583,0.000005860836,0.0006356997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7929775,"threshold_uncertainty_score":0.6730168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1586272169616062,"score_gpt":0.4485291685510012,"score_spread":0.289901951589395,"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."}}