{"id":"W3104327413","doi":"10.1145/3388440.3412418","title":"Global Surveillance of COVID-19 by mining news media using a multi-source dynamic embedded topic model","year":2020,"lang":"en","type":"article","venue":"","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Topic model; Computer science; Social media; News media; Framing (construction); Inference; Latent Dirichlet allocation; Classifier (UML); Digital media; Data science; Artificial intelligence; Machine learning; World Wide Web; Political science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002639473,0.00008179516,0.0001609764,0.00001942578,0.000150167,0.00004794343,0.0001932236,0.00007384222,0.0002648064],"category_scores_gemma":[0.00152316,0.00007665047,0.00004465742,0.000333021,0.00009663508,0.0002318992,0.00003791545,0.00003827878,0.000007887772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001436441,"about_ca_system_score_gemma":0.000469772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002655168,"about_ca_topic_score_gemma":0.005750456,"domain_scores_codex":[0.9990004,0.00008509611,0.0002505205,0.0001203913,0.0003206774,0.0002229375],"domain_scores_gemma":[0.999242,0.00007810567,0.0001255388,0.0000881767,0.0000489123,0.0004172451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000915329,0.0001059599,0.02180074,0.0001552146,0.00005194694,0.000002566017,0.8269849,0.08499344,0.001274908,0.004615214,0.03627556,0.02364804],"study_design_scores_gemma":[0.0006054954,0.00001191592,0.000385385,0.000004875318,0.000003982324,4.613946e-7,0.04768858,0.9448486,0.00001578235,0.00004852238,0.006248402,0.0001380217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.565174,0.00006009834,0.4172439,0.003775839,0.00008014204,0.0001632975,0.00004896182,0.0001110907,0.01334269],"genre_scores_gemma":[0.982962,0.00002349865,0.01173589,0.004737061,0.00002585069,2.914057e-7,0.000009471305,0.000004068756,0.0005018592],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8598551,"threshold_uncertainty_score":0.4013838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09761497201716676,"score_gpt":0.3834688836502118,"score_spread":0.285853911633045,"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."}}