{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009438072,0.001346865,0.0005325391,0.004348241,0.0008844698,0.0007046984,0.000970013,0.001532551,0.003405809],"category_scores_gemma":[0.003225914,0.0002744146,0.0005911069,0.002447793,0.0002871647,0.001493717,0.001402275,0.000885986,0.004367206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009292331,"about_ca_system_score_gemma":0.001087628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0113656,"about_ca_topic_score_gemma":0.02631354,"domain_scores_codex":[0.9989767,0.000221587,0.0001787088,0.0002537287,0.0002679038,0.0001013039],"domain_scores_gemma":[0.998062,0.000634521,0.0003129892,0.0003452874,0.0004589088,0.0001863526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001629165,0.001600878,0.1257747,0.003114402,0.0003521542,0.001803443,0.001461243,0.009540395,0.03823953,0.00412014,0.5691759,0.2431882],"study_design_scores_gemma":[0.0005790537,0.0009154421,0.2198428,0.0004389997,0.0002587395,0.001808523,0.003765704,0.3019495,0.04152212,0.007390383,0.4210605,0.0004682243],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2143301,0.0009972552,0.03065833,0.00234643,0.001030866,0.002204338,0.7119479,0.0215276,0.01495728],"genre_scores_gemma":[0.173772,0.0004648282,0.07648552,0.0008162587,0.0004198387,0.002800956,0.7382479,0.0004728254,0.006519943],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0113656,"threshold_uncertainty_score":0.02259886,"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."}}