{"id":"W4285412885","doi":"10.3934/dsfe.2022009","title":"The informative value of central banks talks: a topic model application to sentiment analysis","year":2022,"lang":"en","type":"article","venue":"Data Science in Finance and Economics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Index (typography); Predictive power; Latent Dirichlet allocation; Monetary policy; Sentiment analysis; Probit model; Central bank; Topic model; Economics; Computer science; Econometrics; Artificial intelligence; Macroeconomics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001882053,0.00003397359,0.00009119943,0.0001232892,0.0006653844,0.00006194744,0.0006711363,0.000007647211,0.000005789557],"category_scores_gemma":[0.00004391043,0.00003044691,0.00002045947,0.001047023,0.0002151624,0.0004849477,0.0004426288,0.00003937146,6.90176e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001070259,"about_ca_system_score_gemma":0.0002153964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007478141,"about_ca_topic_score_gemma":0.00150107,"domain_scores_codex":[0.9993035,0.00003489615,0.0001897895,0.0001881369,0.0001280109,0.0001556709],"domain_scores_gemma":[0.9995207,0.00008647516,0.00009889453,0.0002409612,0.00002253378,0.00003042006],"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":[0.000004971965,0.00001743283,0.01072173,8.707089e-7,0.00001099833,4.841541e-8,0.006886713,0.7796784,0.000004507589,0.1476537,0.00005335221,0.05496732],"study_design_scores_gemma":[0.00003591387,0.000005796712,0.02597939,5.867528e-7,0.00001278811,6.109227e-8,0.001926056,0.9515859,0.000008166789,0.005082498,0.01531964,0.00004314944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9778988,0.00002945546,0.0194155,0.001309141,0.00005786228,0.0001357151,0.000136833,0.000002761628,0.001013874],"genre_scores_gemma":[0.9961038,0.0001504852,0.003474678,0.0001159364,0.000009791714,0.00001864752,0.00002851563,7.341146e-7,0.0000973626],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1719076,"threshold_uncertainty_score":0.5117666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03238549170701941,"score_gpt":0.3408783064250747,"score_spread":0.3084928147180552,"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."}}