{"id":"W4382583924","doi":"10.3389/fdgth.2023.1203874","title":"Comparison of pretrained transformer-based models for influenza and COVID-19 detection using social media text data in Saskatchewan, Canada","year":2023,"lang":"en","type":"article","venue":"Frontiers in Digital Health","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Social media; Coronavirus disease 2019 (COVID-19); Computer science; Transformer; Artificial intelligence; Context (archaeology); Language model; Outbreak; Natural language processing; Machine learning; Medicine; Geography; World Wide Web; Virology; Infectious disease (medical specialty); Disease; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004585576,0.0001438608,0.0006062505,0.000270616,0.00006666934,0.00001591159,0.0001492936,0.0000769466,0.000001226594],"category_scores_gemma":[0.0004450185,0.0001567569,0.00003160638,0.0005616579,0.0001054576,0.0003142505,0.00002980554,0.0001440824,1.025724e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008471276,"about_ca_system_score_gemma":0.005115625,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05786286,"about_ca_topic_score_gemma":0.7306877,"domain_scores_codex":[0.9982968,0.00003974812,0.0005956753,0.0003573423,0.0003201279,0.0003902951],"domain_scores_gemma":[0.9990426,0.0001999952,0.0001538255,0.0002741272,0.00004082956,0.0002886377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004452177,0.0004314849,0.6650428,0.006851292,0.00009479277,0.00002918574,0.009984617,0.01073122,0.00005399108,0.00001418157,0.03458475,0.2677295],"study_design_scores_gemma":[0.007570046,0.0002186722,0.06120951,0.0002436045,0.00002627688,0.000002319637,0.01743131,0.9085312,0.00006784862,0.0008388254,0.003563687,0.0002966763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9098272,0.0005359834,0.07666029,0.0005349781,0.0003103531,0.001324506,0.01069084,0.00007125358,0.00004461133],"genre_scores_gemma":[0.9958792,0.000005658406,0.001504116,0.0006747167,0.0000377942,0.00002015678,0.001848549,0.00002495831,0.000004846725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8978,"threshold_uncertainty_score":0.9484109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1175481210410137,"score_gpt":0.3913340771546693,"score_spread":0.2737859561136556,"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."}}