{"id":"W3126565418","doi":"10.2196/21679","title":"Lexicon Development for COVID-19-related Concepts Using Open-source Word Embedding Sources: An Intrinsic and Extrinsic Evaluation","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institutes of Health; Perelman School of Medicine, University of Pennsylvania; University of Pennsylvania","keywords":"Coronavirus disease 2019 (COVID-19); Lexicon; Computer science; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Word embedding; 2019-20 coronavirus outbreak; Word (group theory); Open source; Natural language processing; Artificial intelligence; Embedding; Linguistics; Medicine; Virology; Software; Pathology; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.001265304,0.0001741378,0.000253195,0.00005307668,0.0002485666,0.0001215907,0.0002978034,0.0004311003,0.0001451847],"category_scores_gemma":[0.001929477,0.0001535825,0.00003859826,0.0001634929,0.0002766449,0.00002240283,0.0004343653,0.0001768533,0.000003074048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006946798,"about_ca_system_score_gemma":0.001939029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005295171,"about_ca_topic_score_gemma":0.00002770405,"domain_scores_codex":[0.9982667,0.0001186586,0.000617945,0.0002358105,0.0004579543,0.0003029278],"domain_scores_gemma":[0.998769,0.00009859398,0.0002047775,0.0002464117,0.0001792756,0.0005018954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007961495,0.0001079569,0.0003237555,0.000199487,0.0001001679,0.000005510097,0.008178285,0.0001165176,0.001375545,0.0001144921,0.001136092,0.9882626],"study_design_scores_gemma":[0.00822599,0.0005111312,0.0004639992,0.0002956352,0.0001088508,0.000345977,0.03055864,0.09525638,0.0120013,0.0005377635,0.850875,0.0008193573],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9559395,0.0008336878,0.04185261,0.0003978694,0.0001639786,0.0005451092,0.000006090702,0.0000428404,0.000218286],"genre_scores_gemma":[0.8969662,0.000281862,0.09374497,0.006952573,0.0002808871,0.0002541045,0.001111985,0.00004393956,0.0003635352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9874432,"threshold_uncertainty_score":0.6262913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07589123149888627,"score_gpt":0.4143356395403869,"score_spread":0.3384444080415006,"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."}}