{"id":"W4220984160","doi":"10.1016/j.patter.2022.100435","title":"Inferring global-scale temporal latent topics from news reports to predict public health interventions for COVID-19","year":2022,"lang":"en","type":"article","venue":"Patterns","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Psychological intervention; Computer science; Public health; Topic model; Scale (ratio); Data science; Public health interventions; Transfer of learning; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Artificial intelligence; Machine learning; Medicine; Infectious disease (medical specialty); Geography","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00138975,0.00007088813,0.0001831806,0.00007408538,0.0008370445,0.00009891589,0.0001861359,0.00002022699,0.0009296948],"category_scores_gemma":[0.0003148151,0.0000763952,0.0002337668,0.0003233352,0.00001921622,0.00008017327,0.0001973556,0.00007112842,0.000002920337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006495549,"about_ca_system_score_gemma":0.0004589483,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05822616,"about_ca_topic_score_gemma":0.07996146,"domain_scores_codex":[0.9983191,0.0004027723,0.0003865616,0.0002765949,0.0003645436,0.0002503938],"domain_scores_gemma":[0.9991166,0.0001213994,0.0001848201,0.0001547198,0.00004449363,0.0003779697],"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":[0.000003237419,0.00009188347,0.9557754,0.00002316696,0.0000389291,0.00000633617,0.005174524,0.0009786165,4.098952e-7,0.001395206,0.003783984,0.03272827],"study_design_scores_gemma":[0.0002368485,0.0001196577,0.2827018,0.00002200089,0.00002841152,0.000003138482,0.004406066,0.0007986988,6.061669e-7,0.02670459,0.6847963,0.0001818689],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2660469,0.0001116164,0.6392056,0.09210055,0.0009677169,0.0005506141,0.000422009,0.000116174,0.0004788535],"genre_scores_gemma":[0.9876913,0.000006184083,0.006412307,0.004177962,0.0003662893,0.000183402,0.0002796213,0.000006055235,0.000876874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7216444,"threshold_uncertainty_score":0.9999836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2092445544913648,"score_gpt":0.4671266355461511,"score_spread":0.2578820810547863,"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."}}