{"id":"W4399091994","doi":"10.3390/a17060234","title":"Unleashing the Power of Tweets and News in Stock-Price Prediction Using Machine-Learning Techniques","year":2024,"lang":"en","type":"article","venue":"Algorithms","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Stock price; Computer science; Stock (firearms); Artificial intelligence; Machine learning; Predictive power; Sentiment analysis; Econometrics; Economics; History","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.007573282,0.0001391648,0.0002426102,0.0004496018,0.0001371468,0.0002495979,0.0003515228,0.00009217297,0.0000661988],"category_scores_gemma":[0.004344847,0.00008771743,0.00006794385,0.001348959,0.0001106942,0.0003576504,0.0002484969,0.0004447494,0.000003585663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005760691,"about_ca_system_score_gemma":0.00005152928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005127054,"about_ca_topic_score_gemma":0.0000305434,"domain_scores_codex":[0.9973385,0.0007017567,0.0005654533,0.0004313615,0.0007436094,0.0002192584],"domain_scores_gemma":[0.9959015,0.00347637,0.0001577276,0.0003112755,0.0001033544,0.00004981459],"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":[0.00002156489,0.00001800423,0.06336185,0.00001696408,0.0000217951,0.00002715472,0.003463052,0.0002756288,0.003627107,0.0001579575,0.0001874609,0.9288214],"study_design_scores_gemma":[0.0002070935,0.0002003032,0.04518961,0.0003934462,0.00003442326,0.0002424723,0.00218466,0.9165895,0.003345927,0.01361722,0.01773265,0.0002627078],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7848913,0.002591056,0.2049127,0.0005301094,0.0009961457,0.0004771705,0.00001726046,0.0002393369,0.005344889],"genre_scores_gemma":[0.8802527,0.00004289152,0.1190815,0.0000508645,0.0001263706,0.00001275298,0.000001108017,0.00002928875,0.0004025478],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9285588,"threshold_uncertainty_score":0.5201501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09190739289537232,"score_gpt":0.3989999113664047,"score_spread":0.3070925184710324,"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."}}