{"id":"W2912627851","doi":"10.2139/ssrn.2976084","title":"Aggregating the Panel of Daily Textual Sentiment for Sparse Forecasting of Economic Growth","year":2017,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke; Center for Interuniversity Research and Analysis on Organizations; HEC Montréal","funders":"","keywords":"Econometrics; Sentiment analysis; Computer science; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009635772,0.0006695253,0.0007793869,0.002357679,0.0002975015,0.0007938388,0.0004508681,0.0007592078,0.00421987],"category_scores_gemma":[0.006577802,0.0002718123,0.0006179806,0.002364163,0.0001580055,0.001082939,0.0006391868,0.0007249629,0.002592756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001795006,"about_ca_system_score_gemma":0.0003669873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003487941,"about_ca_topic_score_gemma":0.005765487,"domain_scores_codex":[0.9995945,0.0001265878,0.00003906986,0.00009696904,0.0000916501,0.00005120573],"domain_scores_gemma":[0.9975756,0.001315903,0.0002679616,0.0003195585,0.0004324097,0.00008861593],"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":[0.001631327,0.0007863907,0.08794149,0.0004604964,0.0005348224,0.0004446673,0.0004254244,0.1306717,0.03140648,0.005564427,0.04234555,0.6977872],"study_design_scores_gemma":[0.00003260265,0.0001796262,0.03725714,0.00003263509,0.0001142359,0.00006723129,0.0001193486,0.9488207,0.003240381,0.005906203,0.004195249,0.00003467976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6194015,0.001467895,0.3384362,0.001270873,0.0007132625,0.0002087141,0.02783189,0.002477682,0.00819197],"genre_scores_gemma":[0.9133072,0.0007248722,0.05094852,0.0001195634,0.0009016613,0.0002237221,0.03025826,0.0000742175,0.003441846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00421987,"threshold_uncertainty_score":0.01411682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1535934690060364,"score_gpt":0.3846360018511181,"score_spread":0.2310425328450817,"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."}}