{"id":"W4365793937","doi":"10.2139/ssrn.4405779","title":"EconSentGPT: A Universal Economic Sentiment Engine?","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Trinity College","funders":"","keywords":"Sentiment analysis; Computer science; Natural language processing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001880879,0.000569765,0.0005076065,0.001022117,0.0001999481,0.002566601,0.0006662501,0.0007903896,0.01650737],"category_scores_gemma":[0.008101263,0.0003147979,0.0003244906,0.001018646,0.0002941862,0.003602068,0.001500299,0.0009484013,0.00735096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002635547,"about_ca_system_score_gemma":0.000453967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007850773,"about_ca_topic_score_gemma":0.0009084914,"domain_scores_codex":[0.9995025,0.0001300099,0.00004229682,0.0001131449,0.0001608111,0.00005115383],"domain_scores_gemma":[0.9991803,0.0002856602,0.00008878471,0.0002073964,0.0001660174,0.00007192845],"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":[0.0009425607,0.0002133463,0.02148761,0.0003881152,0.0001710461,0.0001940274,0.0002205971,0.01205909,0.007687427,0.1018413,0.1189348,0.7358601],"study_design_scores_gemma":[0.0001604379,0.00020989,0.01358509,0.0001844416,0.0001725651,0.0003912465,0.0001265778,0.7139107,0.02060023,0.1352881,0.1152811,0.00008950057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1318042,0.002002915,0.6858136,0.007381587,0.002423641,0.0002975551,0.01512096,0.05589235,0.09926316],"genre_scores_gemma":[0.7725174,0.001476876,0.1812019,0.001466995,0.001085116,0.0002175842,0.009058438,0.002963352,0.03001229],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01650737,"threshold_uncertainty_score":0.05522263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05262775552573903,"score_gpt":0.363331289481746,"score_spread":0.310703533956007,"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."}}