{"id":"W4413832118","doi":"10.2196/79161","title":"Analysis of Breast Cancer Information on Facebook Using Neural Network–Based Topic Modeling and Metadata Analysis of English and Spanish Content: Comparative Study","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Health Literacy and Information Accessibility","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Preprint; Metadata; Computer science; World Wide Web; Breast cancer; Content analysis; Internet privacy; Data science; Information retrieval; Cancer; Medicine; Sociology","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":[0.001972144,0.0003532127,0.0003248549,0.003017334,0.0003112956,0.0009124442,0.000314506,0.0003155738,0.0008275334],"category_scores_gemma":[0.007203166,0.0001159147,0.0007708795,0.001556063,0.0002440969,0.001087456,0.0005597835,0.0002917542,0.0003177783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008018982,"about_ca_system_score_gemma":0.0004564967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01430665,"about_ca_topic_score_gemma":0.01438701,"domain_scores_codex":[0.9992855,0.0003469109,0.00005098635,0.0001449253,0.0001077182,0.00006398616],"domain_scores_gemma":[0.9958234,0.002741893,0.0003698426,0.0001735394,0.0007643485,0.0001270762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008855725,0.0007238102,0.7869024,0.0005196746,0.0003867584,0.0004495269,0.007029034,0.01417494,0.004833058,0.001014635,0.002754419,0.1803262],"study_design_scores_gemma":[0.00002593908,0.0002884227,0.6224352,0.00009559585,0.0002488135,0.0002640819,0.01426298,0.3560041,0.001979394,0.001030636,0.003303187,0.00006178574],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929122,0.0002347173,0.004759485,0.0001093577,0.00001189282,0.00005314999,0.0006255691,0.00006693373,0.00122667],"genre_scores_gemma":[0.9923083,0.0002162212,0.004994166,0.00002139065,0.0000282285,0.00005629783,0.001730283,0.00001922333,0.0006258994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01430665,"threshold_uncertainty_score":0.02844679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3184503892358084,"score_gpt":0.5804969436396211,"score_spread":0.2620465544038127,"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."}}