{"id":"W2895296143","doi":"10.1093/jamia/ocy114","title":"Data and systems for medication-related text classification and concept normalization from Twitter: insights from the Social Media Mining for Health (SMM4H)-2017 shared task","year":2018,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"U.S. National Library of Medicine; National Institutes of Health; National Cancer Institute; Medical Research Council; Engineering and Physical Sciences Research Council; China Scholarship Council","keywords":"Normalization (sociology); Computer science; Social media; F1 score; Artificial intelligence; Machine learning; Identifier; Task (project management); Natural language processing; Context (archaeology); World Wide Web","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003543291,0.0001091308,0.0003358497,0.00006568981,0.001187511,0.0003050618,0.000661035,0.00014307,0.00001620993],"category_scores_gemma":[0.01193068,0.00006875071,0.0000528284,0.0002637573,0.0005247869,0.0009698897,0.00008898997,0.0001982941,0.000002024236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000294741,"about_ca_system_score_gemma":0.000804196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004137515,"about_ca_topic_score_gemma":0.0004635219,"domain_scores_codex":[0.9969094,0.0003628442,0.001168307,0.00008667065,0.001247517,0.0002252358],"domain_scores_gemma":[0.9912602,0.002863295,0.004874549,0.0002001305,0.0005722474,0.0002295442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00007067049,0.00003391526,0.002384703,0.00002326482,0.0002495121,6.742804e-8,0.6381291,0.0000047863,0.00001670019,0.001850301,0.3257795,0.0314575],"study_design_scores_gemma":[0.003436104,0.0002543631,0.163727,0.0004541081,0.0002951442,0.000005223994,0.3643969,0.286919,0.000007199493,0.002042658,0.1781361,0.0003262181],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8689294,0.0006415884,0.04484665,0.07982951,0.002640108,0.001281267,0.001311186,0.00004150031,0.0004787378],"genre_scores_gemma":[0.9909354,0.0008503689,0.001142908,0.004872618,0.001677364,0.000006174233,0.0004729232,0.000010106,0.00003207611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2869142,"threshold_uncertainty_score":0.9963923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07127753204526234,"score_gpt":0.3749801132463712,"score_spread":0.3037025812011089,"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."}}