{"id":"W3137246643","doi":"10.1007/s41666-021-00097-5","title":"Analyzing Patient Stories on Social Media Using Text Analytics","year":2021,"lang":"en","type":"article","venue":"Journal of Healthcare Informatics Research","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; Regional Municipality of Waterloo; University of Waterloo","funders":"","keywords":"Social media; Health care; Latent Dirichlet allocation; Quality (philosophy); Sentiment analysis; Topic model; Analytics; Workload; Psychology; Computer science; Data science; World Wide Web; Artificial intelligence; Political science","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005013505,0.0002235325,0.0007193743,0.001313468,0.002723808,0.00005747165,0.0003435747,0.0004388541,0.000245116],"category_scores_gemma":[0.005149248,0.0001963233,0.0001989665,0.001842522,0.0001574136,0.0005774904,0.0002625549,0.005064441,0.0001173462],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003263197,"about_ca_system_score_gemma":0.007203059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002608885,"about_ca_topic_score_gemma":0.0005175598,"domain_scores_codex":[0.9893948,0.002855707,0.003367002,0.000153805,0.002998143,0.001230485],"domain_scores_gemma":[0.9829038,0.004357582,0.001858373,0.0004192283,0.00982583,0.0006352108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.001167465,0.0002912487,0.4396385,0.01031304,0.0004149743,0.0004435685,0.3625477,0.001961441,0.0001713082,0.01484914,0.03455019,0.1336515],"study_design_scores_gemma":[0.003915735,0.001928534,0.09110383,0.008119783,0.0001021639,0.0002834467,0.8082427,0.007510788,0.0006227345,0.00438658,0.07281835,0.0009653108],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9872463,0.0007301339,0.000461525,0.006476438,0.003142087,0.0004849185,0.0001018731,0.00002864481,0.001328023],"genre_scores_gemma":[0.9931328,0.0006458822,0.004009849,0.0008639271,0.001209873,0.00001274222,0.00002720975,0.00004201502,0.00005575678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4456951,"threshold_uncertainty_score":0.9985745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4561559312256841,"score_gpt":0.5765540087634238,"score_spread":0.1203980775377397,"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."}}