{"id":"W2474779893","doi":"10.2196/medinform.5490","title":"A Semi-Supervised Learning Approach to Enhance Health Care Community–Based Question Answering: A Case Study in Alcoholism","year":2016,"lang":"en","type":"preprint","venue":"JMIR Medical Informatics","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine","keywords":"Question answering; Computer science; Set (abstract data type); Information retrieval; Unified Medical Language System; Rank (graph theory); Test (biology); Similarity (geometry); Artificial intelligence; Baseline (sea); String metric; Test set; Natural language processing; Machine learning; String searching algorithm; Mathematics","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":[0.007654066,0.0004521835,0.000413234,0.001336963,0.001283898,0.000757981,0.001482321,0.001575983,0.001644437],"category_scores_gemma":[0.02056117,0.0002059363,0.0005498897,0.001052842,0.000784937,0.00128706,0.001148527,0.001099032,0.0004289587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00137222,"about_ca_system_score_gemma":0.00155246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01011993,"about_ca_topic_score_gemma":0.01845792,"domain_scores_codex":[0.9937524,0.004800216,0.0002740788,0.0004593815,0.0005331305,0.0001807407],"domain_scores_gemma":[0.9663499,0.02648103,0.0009916715,0.001326608,0.004075371,0.0007754408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001555641,0.008269818,0.1249758,0.001995309,0.0002281639,0.007222866,0.03130981,0.06389908,0.02275521,0.004561279,0.0185726,0.7146545],"study_design_scores_gemma":[0.000347043,0.001529873,0.05468393,0.0001718755,0.0001303689,0.002826623,0.01400825,0.865405,0.02521971,0.008133891,0.02739407,0.0001492758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8711414,0.000435275,0.1182814,0.003146906,0.00005625299,0.000883779,0.0006654393,0.001362924,0.004026601],"genre_scores_gemma":[0.8655412,0.0001160258,0.1310558,0.0002579845,0.00004255938,0.0003045828,0.0008076009,0.00006255901,0.001811712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01011993,"threshold_uncertainty_score":0.04047906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04537685676127573,"score_gpt":0.37189076878779,"score_spread":0.3265139120265143,"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."}}