{"id":"W3034078763","doi":"10.2196/19273","title":"Tracking Social Media Discourse About the COVID-19 Pandemic: Development of a Public Coronavirus Twitter Data Set","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":523,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency","keywords":"Misinformation; Social media; Context (archaeology); Set (abstract data type); Tracking (education); Conversation; Coronavirus disease 2019 (COVID-19); Coronavirus","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.003130082,0.0004852243,0.0004608452,0.006383691,0.001665401,0.001748979,0.001295555,0.00136312,0.002131143],"category_scores_gemma":[0.01121293,0.0003755433,0.0005217039,0.005197626,0.0008936781,0.003087793,0.004596882,0.001630711,0.003853359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009864677,"about_ca_system_score_gemma":0.001500317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0123888,"about_ca_topic_score_gemma":0.01993764,"domain_scores_codex":[0.9961801,0.001316948,0.0004892281,0.0006413946,0.001063235,0.0003090853],"domain_scores_gemma":[0.9897748,0.002997809,0.001054334,0.001591786,0.003257587,0.001323564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001198726,0.00258788,0.3909543,0.003352437,0.0002713623,0.002870785,0.02487325,0.005346413,0.02705194,0.007944918,0.297138,0.2364101],"study_design_scores_gemma":[0.0002021383,0.0007778172,0.5800641,0.0005708539,0.0001476556,0.001093383,0.02771065,0.03230836,0.01445247,0.002856896,0.3394667,0.0003490206],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.6767004,0.000545294,0.0109083,0.004134094,0.000449129,0.003106604,0.2908255,0.002129633,0.01120108],"genre_scores_gemma":[0.356944,0.0005253226,0.05642837,0.0008071298,0.0004366432,0.006447091,0.5713853,0.0004952254,0.006530937],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.9987044,"threshold_uncertainty_score":0.02463335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5085554674457192,"score_gpt":0.4794237251615806,"score_spread":0.02913174228413862,"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."}}