{"id":"W4360610310","doi":"10.1186/s12913-023-09260-7","title":"Development of a patients’ satisfaction analysis system using machine learning and lexicon-based methods","year":2023,"lang":"en","type":"article","venue":"BMC Health Services Research","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; University of British Columbia","funders":"","keywords":"tf–idf; Naive Bayes classifier; Artificial intelligence; Lexicon; Sentiment analysis; Medicine; Natural language processing; Precision and recall; Stop words; Computer science; Machine learning; Receiver operating characteristic; Support vector machine; Preprocessor","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"],"consensus_categories":[],"category_scores_codex":[0.01078746,0.0002054614,0.0006893434,0.002322793,0.003153316,0.00001651348,0.0001670371,0.0002491936,0.0001268764],"category_scores_gemma":[0.000176087,0.0001971279,0.00007473393,0.00474897,0.00006160304,0.0001416308,0.000276675,0.001129742,0.00007903587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001510075,"about_ca_system_score_gemma":0.00281415,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01684208,"about_ca_topic_score_gemma":0.01445515,"domain_scores_codex":[0.9865778,0.00886699,0.001620247,0.000577822,0.001205843,0.001151272],"domain_scores_gemma":[0.9942695,0.003038483,0.0007946368,0.0003740342,0.001046856,0.000476425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000108214,0.0000127882,0.9656841,0.01688354,0.00006964123,3.465518e-7,0.008705856,0.0004987061,0.00008579762,0.00007835208,0.000002041479,0.007870644],"study_design_scores_gemma":[0.0005736956,0.00007519807,0.7653829,0.0007041934,0.00002061215,8.462059e-8,0.01550386,0.2170145,0.00004378991,0.000007260769,0.000569273,0.0001045823],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900614,0.0002394264,0.007154818,0.00006464382,0.0003063252,0.001784961,0.00007057238,0.0002484916,0.00006935521],"genre_scores_gemma":[0.9169263,0.00005582993,0.08220293,0.00009023481,0.00004997256,0.0002854036,0.0002892432,0.00004527733,0.0000548297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2165158,"threshold_uncertainty_score":0.9981444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2551594021000083,"score_gpt":0.5809053128095992,"score_spread":0.325745910709591,"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."}}