{"id":"W824559114","doi":"10.2196/resprot.3433","title":"Collecting and Analyzing Patient Experiences of Health Care From Social Media","year":2015,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sentiment analysis; Social media; Health care; Computer science; Vocabulary; Sentence; Natural language processing; Dependency grammar; Bottleneck; Noun; Artificial intelligence; Psychology; Parsing; Data science; World Wide Web; Linguistics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.00225155,0.0001374819,0.0004215662,0.0003057779,0.00182188,0.00002022266,0.0002034227,0.000196596,0.0001820613],"category_scores_gemma":[0.001705615,0.0001229031,0.00003576869,0.0007392444,0.0002445586,0.0001803955,0.0003298219,0.001046597,0.00002641482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000793392,"about_ca_system_score_gemma":0.002458734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001816094,"about_ca_topic_score_gemma":0.0006634376,"domain_scores_codex":[0.9919688,0.004609438,0.0009583252,0.0004044589,0.001242393,0.0008166168],"domain_scores_gemma":[0.9957744,0.001723236,0.0005068496,0.000273621,0.001315432,0.00040642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001961168,0.00002876485,0.2440873,0.0006694868,0.000006598133,0.000001374756,0.7264714,4.29184e-7,0.00002481007,0.0000884124,0.01032179,0.01810361],"study_design_scores_gemma":[0.001579135,0.0008270326,0.04740962,0.002247797,6.969983e-7,2.566365e-7,0.9268587,0.00001956603,0.0001703863,0.0004746223,0.02026642,0.0001457111],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"protocol","genre_scores_codex":[0.6653576,0.000122289,0.00001457463,0.0005792322,0.00009047444,0.3326407,0.00006691091,0.00006993937,0.001058201],"genre_scores_gemma":[0.4293537,9.735985e-7,0.000341574,0.00004945802,0.0001615481,0.5700434,0.00001604359,0.00001606751,0.00001726212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2374026,"threshold_uncertainty_score":0.9994776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6334939196809266,"score_gpt":0.670449864846763,"score_spread":0.03695594516583645,"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."}}