{"id":"W4389256182","doi":"10.16995/dscn.10231","title":"Ecological Modelling: Applying Computational Linguistic Analysis to the UN Secretary-General’s Speeches on Climate Change (2018–2022)","year":2023,"lang":"en","type":"article","venue":"Digital Studies / Le champ numérique","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Latent Dirichlet allocation; Climate change; Humanities; Topic model; Sociology; Philosophy; Computer science; Ecology; Artificial intelligence; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001517728,0.0002288274,0.00045313,0.0003150946,0.001437748,0.0002305499,0.0003466894,0.00007940029,0.0000314598],"category_scores_gemma":[0.0007373499,0.000169662,0.0003512881,0.00277417,0.0002032014,0.0001231781,0.0002909893,0.0001761892,0.0001927638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001301934,"about_ca_system_score_gemma":0.00005647779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003233446,"about_ca_topic_score_gemma":0.001046707,"domain_scores_codex":[0.9976547,0.0002982639,0.0003696819,0.0005114551,0.0006531344,0.0005127215],"domain_scores_gemma":[0.9976285,0.001610106,0.0001320637,0.0001773956,0.0003017846,0.0001502136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003670367,0.0001699701,0.005975709,0.0000168366,0.001631778,0.0000461034,0.2424933,0.7119969,0.000001059261,0.01310348,0.000631595,0.02389665],"study_design_scores_gemma":[0.0004131936,0.0002018526,0.01912822,0.00004737782,0.00003187555,0.000001984486,0.2755075,0.3901152,0.00001331969,0.2510018,0.06254093,0.0009967941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9216477,0.0005415785,0.04590544,0.01625906,0.0006234293,0.0009495462,0.0001699277,0.0004433692,0.01345991],"genre_scores_gemma":[0.9963121,0.0003736216,0.0005329203,0.0007956367,0.0009379886,0.0002674261,0.0001806719,0.00001625946,0.0005833578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3218817,"threshold_uncertainty_score":0.9998623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1442261892630486,"score_gpt":0.3693065111214384,"score_spread":0.2250803218583898,"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."}}