{"id":"W3090950362","doi":"10.1111/1468-5973.12311","title":"Using deep learning and social network analysis to understand and manage extreme flooding","year":2020,"lang":"en","type":"article","venue":"Journal of Contingencies and Crisis Management","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Environment Canada","keywords":"Leverage (statistics); Computer science; Social media; Flooding (psychology); Artificial intelligence; Machine learning; Data science; Flood myth; Train; Generalization; Social network analysis; Deep learning; World Wide Web; Geography; Cartography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001077387,0.00008005248,0.0002261601,0.000162746,0.0009781686,0.0003800539,0.0001172727,0.00003719041,0.00002094332],"category_scores_gemma":[0.00004033058,0.00007706445,0.00006709906,0.0005844092,0.00005887994,0.0002658539,0.0001705566,0.000120192,2.309341e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004189523,"about_ca_system_score_gemma":0.000007927721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000710934,"about_ca_topic_score_gemma":0.0001702636,"domain_scores_codex":[0.9989725,0.0001592015,0.0002939962,0.0001269954,0.0002645514,0.0001827208],"domain_scores_gemma":[0.9994251,0.00005117583,0.0002598272,0.00004669855,0.00009407769,0.0001231594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001668643,0.0001001812,0.1262947,0.0002427454,0.005834104,0.00005409545,0.3442564,0.009257132,0.0002436139,0.2724256,0.006716394,0.2344081],"study_design_scores_gemma":[0.0006756499,0.0001213636,0.04599148,0.00004418373,0.00276728,0.000003254044,0.7630774,0.01131553,0.000001525236,0.003079593,0.1725644,0.0003583471],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.829459,0.006560559,0.1211227,0.0288758,0.00008302619,0.0002290817,6.123967e-7,0.0000250253,0.01364418],"genre_scores_gemma":[0.9900486,0.00308094,0.006230159,0.0004151851,0.0001530534,6.564707e-7,3.968165e-7,0.000005168182,0.0000658387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4188209,"threshold_uncertainty_score":0.7523381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0786037246207103,"score_gpt":0.3223428986900334,"score_spread":0.2437391740693231,"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."}}