{"id":"W3041699688","doi":"10.1371/journal.pone.0239441","title":"Public discourse and sentiment during the COVID 19 pandemic: Using Latent Dirichlet Allocation for topic modeling on Twitter","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":355,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Toronto; National Natural Science Foundation of China","keywords":"Latent Dirichlet allocation; Topic model; Sentiment analysis; Pandemic; Coronavirus disease 2019 (COVID-19); Social media; Outbreak; Public health; Coronavirus; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Cruise; Geography; Psychology; Medicine; History; Computer science; Natural language processing; Virology; Pathology; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004496179,0.0005874397,0.0006268139,0.002142903,0.000850133,0.002322029,0.0005376401,0.001044576,0.001186654],"category_scores_gemma":[0.01326039,0.0003471525,0.001048967,0.001902251,0.0006924325,0.002707411,0.001312997,0.001311625,0.0005590711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001179835,"about_ca_system_score_gemma":0.0006472597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00623715,"about_ca_topic_score_gemma":0.00533839,"domain_scores_codex":[0.997086,0.002087866,0.0001243559,0.0003787361,0.0001510211,0.0001720232],"domain_scores_gemma":[0.9869053,0.0117769,0.0006265229,0.0002772448,0.0002602285,0.0001538819],"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":[0.003456254,0.00186026,0.3969457,0.001225766,0.001000816,0.0008002108,0.02742053,0.1768783,0.01406557,0.02144796,0.01207963,0.342819],"study_design_scores_gemma":[0.00003768156,0.0001269317,0.04757929,0.00007053537,0.00008122816,0.0000822156,0.004178473,0.9348494,0.001352655,0.008661912,0.002909171,0.00007045006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9309993,0.0006602965,0.05999188,0.002768948,0.0001216189,0.0002148169,0.001837089,0.0002350705,0.003170974],"genre_scores_gemma":[0.9837378,0.0002093736,0.01370503,0.0001181558,0.0001296394,0.0001592636,0.00126735,0.00002439044,0.0006490189],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00623715,"threshold_uncertainty_score":0.02377832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4339952009345251,"score_gpt":0.3687804757839991,"score_spread":0.06521472515052595,"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."}}