{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01173851,0.00309676,0.001682909,0.003554208,0.002532481,0.002063532,0.00334492,0.003355796,0.004516674],"category_scores_gemma":[0.02881584,0.0008730295,0.002545847,0.002286171,0.001038203,0.004216767,0.006458457,0.003051374,0.00702969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002425002,"about_ca_system_score_gemma":0.003786204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01261026,"about_ca_topic_score_gemma":0.01680974,"domain_scores_codex":[0.9891244,0.00360827,0.001230706,0.002733543,0.002623638,0.0006794331],"domain_scores_gemma":[0.9813225,0.007488518,0.00130447,0.003913582,0.004768488,0.001202424],"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":[0.00385338,0.005730614,0.07381959,0.003755862,0.001038242,0.001385748,0.002847623,0.02836529,0.05863078,0.002927263,0.2300862,0.5875594],"study_design_scores_gemma":[0.00130418,0.00275989,0.09335748,0.0006284488,0.0007864939,0.001412321,0.002787168,0.6000148,0.1403638,0.01142381,0.1445154,0.0006462212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.565107,0.003870054,0.1717091,0.008664081,0.002270454,0.008008393,0.1511012,0.07682817,0.01244148],"genre_scores_gemma":[0.3971444,0.0005479826,0.282807,0.00108673,0.0006360415,0.005934094,0.3050277,0.001579932,0.005236115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01261026,"threshold_uncertainty_score":0.06207991,"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."}}