{"id":"W4404845712","doi":"10.2196/59249","title":"Analyzing Patient Experience on Weibo: Machine Learning Approach to Topic Modeling and Sentiment Analysis","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sentiment analysis; Computer science; Health care; Social media; Artificial intelligence; Naive Bayes classifier; Random forest; Psychology; Machine learning; World Wide Web; Political science","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":[0.008686265,0.001313937,0.001118707,0.008836289,0.001132759,0.001950318,0.0009726028,0.001035596,0.002242093],"category_scores_gemma":[0.01555265,0.0004200632,0.001819281,0.005551559,0.0006078847,0.001691898,0.0009428679,0.001204984,0.00121382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001518489,"about_ca_system_score_gemma":0.0008794063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009161412,"about_ca_topic_score_gemma":0.007206096,"domain_scores_codex":[0.9958671,0.00209073,0.0004423963,0.0007277117,0.000644493,0.0002275984],"domain_scores_gemma":[0.9858608,0.01097831,0.001118629,0.0005757704,0.001280621,0.0001858203],"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":[0.001102735,0.0007652138,0.216483,0.0008358259,0.0007038718,0.001084705,0.007703933,0.1481265,0.009896141,0.01159256,0.02136267,0.5803428],"study_design_scores_gemma":[0.00001482284,0.00008211231,0.02688278,0.00004885148,0.00004348149,0.0001293767,0.001019232,0.9605499,0.001298698,0.005909276,0.003959412,0.00006205638],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3922528,0.001121427,0.585726,0.001347086,0.0002911203,0.001362531,0.008396724,0.003649583,0.005852625],"genre_scores_gemma":[0.7815018,0.0003853954,0.2085451,0.0001213752,0.0002740161,0.001048126,0.005904687,0.0001588387,0.002060761],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009161412,"threshold_uncertainty_score":0.0459379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06388676955959254,"score_gpt":0.4274109727544221,"score_spread":0.3635242031948296,"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."}}