{"id":"W4317712920","doi":"10.1111/risa.14100","title":"Textual data transformations using natural language processing for risk assessment","year":2023,"lang":"en","type":"article","venue":"Risk Analysis","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Robustness (evolution); Data mining; Natural language; Risk assessment; Natural language processing; Artificial intelligence; Data science; Risk analysis (engineering); Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.006512973,0.0002068392,0.0006482377,0.00176001,0.001246855,0.0006238791,0.001483401,0.00008728231,0.0001913133],"category_scores_gemma":[0.00189687,0.0001496886,0.0007331469,0.01151862,0.00007889908,0.001173666,0.0002004051,0.0002765284,0.0001276442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006453558,"about_ca_system_score_gemma":0.0001510146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001080636,"about_ca_topic_score_gemma":0.003563418,"domain_scores_codex":[0.9959135,0.0004137038,0.0009941574,0.0007974404,0.001453041,0.0004281631],"domain_scores_gemma":[0.9959568,0.001376141,0.0006232825,0.001517974,0.0003960908,0.0001296547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000293298,0.00006727856,0.07280809,0.000009708113,0.002164972,0.000006468895,0.002550091,0.1766074,0.0001365757,0.00008994697,0.00322892,0.7423012],"study_design_scores_gemma":[0.0002512445,0.000009443233,0.0289639,0.000004102303,0.004948517,7.275049e-7,0.01104142,0.9509801,0.00002133312,0.001318828,0.002259597,0.0002008423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2586458,0.0008697169,0.7360365,0.00079142,0.00007664559,0.0002432516,0.002650101,0.0001582499,0.0005283763],"genre_scores_gemma":[0.9785998,0.0006498812,0.01876306,0.00003575717,0.0001186226,0.00001373939,0.001175188,0.00001454295,0.0006294028],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7743726,"threshold_uncertainty_score":0.9589925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1415213877390253,"score_gpt":0.4793188270300244,"score_spread":0.337797439290999,"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."}}