{"id":"W4229017629","doi":"10.1080/00207543.2022.2070044","title":"Managing demand volatility of pharmaceutical products in times of disruption through news sentiment analysis","year":2022,"lang":"en","type":"article","venue":"International Journal of Production Research","topic":"Supply Chain Resilience and Risk Management","field":"Business, Management and Accounting","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Sentiment analysis; Leverage (statistics); Volatility (finance); Computer science; Coronavirus disease 2019 (COVID-19); Demand forecasting; Data science; Unstructured data; Operations research; Big data; Artificial intelligence; Data mining; Economics; Engineering; Financial economics","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":[0.003833556,0.00008370671,0.0002320373,0.001875315,0.00009935223,0.00005586249,0.000505222,0.00001745413,0.001071759],"category_scores_gemma":[0.0003599705,0.00007446834,0.0001293133,0.002104661,0.0001220373,0.0008343019,0.0004289932,0.0003501527,0.00000418809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001727673,"about_ca_system_score_gemma":0.00005475716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005723158,"about_ca_topic_score_gemma":0.00003692535,"domain_scores_codex":[0.9967772,0.000144448,0.000706262,0.0002477275,0.001938425,0.0001859043],"domain_scores_gemma":[0.9979362,0.00005468298,0.0005133696,0.000182026,0.001303351,0.00001034027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00233944,0.003121712,0.7464739,0.000560694,0.002155164,0.000127193,0.001752978,0.1670196,0.01373164,0.01295478,0.01252751,0.03723542],"study_design_scores_gemma":[0.007825265,0.0006289253,0.3469402,0.0005921486,0.001866958,0.0001147482,0.04498462,0.1917602,0.06798613,0.09448409,0.2416423,0.001174335],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9786894,0.0003724768,0.0008333037,0.01700583,0.001105879,0.0003591523,0.00000325389,0.000007087453,0.001623661],"genre_scores_gemma":[0.9984512,0.0001593515,0.0002761874,0.00005655689,0.0006173203,0.00001172259,0.0000104446,0.000007042448,0.0004101363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3995337,"threshold_uncertainty_score":0.9998414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08119431440669006,"score_gpt":0.4044796318259811,"score_spread":0.323285317419291,"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."}}