{"id":"W2740216362","doi":"10.2196/medinform.7779","title":"What Patients Can Tell Us: Topic Analysis for Social Media on Breast Cancer","year":2017,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Mental Health via Writing","field":"Psychology","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Social media; Breast cancer; Latent Dirichlet allocation; Quality of life (healthcare); Topic model; Jaccard index; Cancer; Public health; Computer science; Medicine; Psychology; Artificial intelligence; World Wide Web; Pathology; Internal medicine; Nursing; Cluster analysis","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003529243,0.000160728,0.0003746499,0.0001261256,0.0005049203,0.0001405344,0.0005138151,0.0002869999,0.002245827],"category_scores_gemma":[0.0001180513,0.000136186,0.0001440378,0.0001120667,0.0001604282,0.0003146066,0.00009856462,0.0003111596,0.0001119752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001624651,"about_ca_system_score_gemma":0.00009467424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001743994,"about_ca_topic_score_gemma":0.0006971157,"domain_scores_codex":[0.9979287,0.00003270524,0.0006910278,0.0001341773,0.0007160234,0.0004973685],"domain_scores_gemma":[0.9984161,0.0002117699,0.0004905121,0.0004139237,0.0001046838,0.0003630426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002843775,0.0006042922,0.35018,0.0006094975,0.0006616064,0.000008536386,0.07052653,0.000001553873,2.217391e-7,0.001970981,0.0336921,0.5414603],"study_design_scores_gemma":[0.002847918,0.0001082398,0.9762539,0.000219247,0.0001581377,0.000002967588,0.007501553,0.00110343,0.000006969364,0.0001080569,0.0114212,0.0002683382],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9878188,0.00001630686,0.00004520745,0.002811025,0.002815265,0.0005677078,0.0002556558,0.0000405888,0.005629487],"genre_scores_gemma":[0.9924198,0.00003328181,0.0001048498,0.005686607,0.0009181264,0.0003479324,0.0001611898,0.00001607099,0.0003120897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6260739,"threshold_uncertainty_score":0.9986662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05341996232095738,"score_gpt":0.424928659255484,"score_spread":0.3715086969345266,"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."}}