{"id":"W4400411032","doi":"10.1016/j.heliyon.2024.e34103","title":"COVIDHealth: A novel labeled dataset and machine learning-based web application for classifying COVID-19 discourses on Twitter","year":2024,"lang":"en","type":"article","venue":"Heliyon","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); World Wide Web; Computer science; Virology; Medicine; Internal medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.0007472928,0.00009349029,0.0001008171,0.0001191302,0.0005050753,0.0002058814,0.00008855579,0.00007324117,0.0001051948],"category_scores_gemma":[0.0006180605,0.00007930757,0.00002531341,0.0001903863,0.00008621051,0.0002212058,0.00001380859,0.0001111721,0.00006982791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381331,"about_ca_system_score_gemma":0.0005525965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003304373,"about_ca_topic_score_gemma":0.001196255,"domain_scores_codex":[0.9991269,0.00006034428,0.0001649801,0.000189051,0.000240501,0.0002182428],"domain_scores_gemma":[0.9991444,0.0004047399,0.00006489856,0.0001127626,0.00002430105,0.0002488442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001666145,0.000954442,0.003794373,0.01719079,0.0001797898,0.00001471637,0.118581,0.005173984,0.01636657,0.3019416,0.4481938,0.08594282],"study_design_scores_gemma":[0.0005947789,0.00008734086,0.00009060503,0.00009705094,0.00001265494,7.580945e-7,0.001146396,0.02147224,0.00008485928,0.00006446838,0.9762381,0.0001107211],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1733563,0.00673465,0.4108883,0.3651164,0.002034269,0.008412283,0.01633926,0.002344186,0.01477438],"genre_scores_gemma":[0.9800756,0.0004142864,0.0003146797,0.01606399,0.0002201198,0.00004846379,0.001984182,0.00001770954,0.0008609935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8067193,"threshold_uncertainty_score":0.3884682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1195148438029554,"score_gpt":0.4199753572339845,"score_spread":0.3004605134310291,"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."}}