{"id":"W4281680075","doi":"10.1371/journal.pone.0268669","title":"Dynamic topic modeling of twitter data during the COVID-19 pandemic","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; UK Research and Innovation; New York University Shanghai","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Data science; Social media; Computer science; Biology; Medicine; Virology; World Wide Web; Outbreak; Infectious disease (medical specialty)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003352801,0.00008161052,0.0002285956,0.0000514898,0.0001267294,0.000005857333,0.0004678229,0.00001722204,0.0006183318],"category_scores_gemma":[0.0002969169,0.00006585265,0.00003288034,0.0001410112,0.00003985575,0.00005357877,0.000752943,0.0002295352,0.00001469568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001541912,"about_ca_system_score_gemma":0.0001339291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008872544,"about_ca_topic_score_gemma":0.00002398032,"domain_scores_codex":[0.9987922,0.00008830753,0.0002210454,0.0002734242,0.0004591503,0.000165891],"domain_scores_gemma":[0.9984252,0.00007148372,0.00007084246,0.001304049,0.00002987813,0.00009848951],"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":[0.0007769101,0.00234164,0.9164535,0.00234129,0.001221214,0.0001592719,0.001509549,0.007668436,0.06555023,0.00003102912,0.001586161,0.0003607353],"study_design_scores_gemma":[0.004472168,0.0001719637,0.05484171,0.0001835416,0.0007898357,0.0001035087,0.0009857201,0.9343734,0.0001900162,0.0003392799,0.003155305,0.0003935077],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964783,0.0004535037,0.0002409299,0.001623249,0.00003028119,0.0003245339,0.0005410715,0.00008839557,0.0002197039],"genre_scores_gemma":[0.9966885,0.00007148724,0.0003608881,0.001514349,0.00004407715,0.00003755075,0.0005866731,0.00001828599,0.0006781246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.926705,"threshold_uncertainty_score":0.67703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1691143786469432,"score_gpt":0.3242153130349569,"score_spread":0.1551009343880138,"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."}}