{"id":"W4241228865","doi":"10.1093/jjfinec/nbz037","title":"Does High-Frequency Social Media Data Improve Forecasts of Low-Frequency Consumer Confidence Measures?","year":2019,"lang":"en","type":"article","venue":"Journal of Financial Econometrics","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Estimator; Consumer confidence index; Discounting; Computer science; Econometrics; Index (typography); Social media; Measure (data warehouse); Sample (material); Sampling (signal processing); Sentiment analysis; Statistics; Data mining; Machine learning; Economics; Finance; Mathematics; Marketing; Business","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005270936,0.0002059303,0.0008346566,0.001245387,0.0001222777,0.000152276,0.003058013,0.0002223372,0.0003964248],"category_scores_gemma":[0.0207602,0.0001320356,0.0002436867,0.002390878,0.0002567494,0.001039065,0.0003436837,0.0004385516,0.00008702676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001186629,"about_ca_system_score_gemma":0.0008239379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006801786,"about_ca_topic_score_gemma":0.00008489786,"domain_scores_codex":[0.9957751,0.0000855583,0.00215064,0.0004700177,0.001185977,0.0003326823],"domain_scores_gemma":[0.9914091,0.002341481,0.003160413,0.001116686,0.001804216,0.0001680954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001910587,0.0006350152,0.07770479,0.0001235358,0.0001119799,0.00004003439,0.001022414,0.00003359281,0.009539994,0.178774,0.02528837,0.7065352],"study_design_scores_gemma":[0.002469005,0.0007477917,0.1308828,0.0002104766,0.0001450226,0.00008428493,0.0004324859,0.0006884508,0.01003961,0.8313165,0.0220047,0.0009789114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9764,0.0005473198,0.01481169,0.00100309,0.003515046,0.0004324805,0.00117862,0.00002555965,0.002086252],"genre_scores_gemma":[0.9849851,0.0001642453,0.01409862,0.00009168681,0.0005203302,0.000004306934,0.00001156763,0.00001738763,0.0001067303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7055563,"threshold_uncertainty_score":0.9874883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1485670598544888,"score_gpt":0.3442444046208788,"score_spread":0.19567734476639,"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."}}