{"id":"W1525023432","doi":"10.15353/rea.v6i2.1416","title":"A Sentiment Analysis of Twitter Content as a Predictor of Exchange Rate Movements","year":2015,"lang":"en","type":"article","venue":"Review of Economic Analysis","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Social media; Currency; Exchange rate; Sentiment analysis; Microblogging; Content (measure theory); Advertising; Content analysis; Business; Economics; Monetary economics; Psychology; Computer science; Sociology; Mathematics; Artificial intelligence; World Wide Web; Social science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01579178,0.0002067043,0.002773703,0.001790332,0.00001805434,0.00001946863,0.000789794,0.00005352664,0.004783793],"category_scores_gemma":[0.003561829,0.0001540756,0.001944956,0.003567952,0.0001286161,0.0001365354,0.0002659324,0.00005597309,0.00006058471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001401853,"about_ca_system_score_gemma":0.0001323396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000560666,"about_ca_topic_score_gemma":0.00007094758,"domain_scores_codex":[0.9945925,0.00106957,0.002828141,0.000555125,0.0007476931,0.0002068959],"domain_scores_gemma":[0.9934538,0.001166573,0.003177197,0.001321763,0.000693555,0.0001870871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002371118,0.0004684115,0.8493334,0.001629256,0.0777097,0.000004898243,0.001456045,0.006517204,0.000380449,0.0003680114,0.01591122,0.04598429],"study_design_scores_gemma":[0.004629257,0.001159485,0.4798662,0.003919699,0.1899527,0.000004587034,0.00252698,0.2599869,0.005555252,0.006869755,0.04382781,0.00170135],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9573982,0.02482371,0.009477437,0.0003698763,0.0002145157,0.0006404007,0.0002160825,0.00001131585,0.00684851],"genre_scores_gemma":[0.9781278,0.007912729,0.006509971,0.001031876,0.00005843507,0.00007322655,0.00006249798,0.00002556219,0.006197864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3694672,"threshold_uncertainty_score":0.996126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.28324760157823,"score_gpt":0.4407361306802506,"score_spread":0.1574885291020206,"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."}}