{"id":"W4387502703","doi":"10.3390/jrfm16100440","title":"Lightweight Scheme to Capture Stock Market Sentiment on Social Media Using Sparse Attention Mechanism: A Case Study on Twitter","year":2023,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Stock market; Sentiment analysis; Social media; Computer science; Stock market prediction; Profit (economics); Financial market; Stock (firearms); Business; Artificial intelligence; Finance; Economics; Microeconomics; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.008448312,0.0002673434,0.000515732,0.001322852,0.0004948524,0.000230418,0.0003498518,0.0000943569,0.00009555145],"category_scores_gemma":[0.001358834,0.000196124,0.0001866065,0.001262154,0.00002994074,0.0001422878,0.0003519739,0.0003803319,0.00005475224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001324519,"about_ca_system_score_gemma":0.00003158467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002525856,"about_ca_topic_score_gemma":0.00003761101,"domain_scores_codex":[0.9955577,0.0007162236,0.0009430032,0.0004877503,0.001923322,0.0003719566],"domain_scores_gemma":[0.9977111,0.000854011,0.0007217882,0.0003079353,0.0002138733,0.0001913096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003161225,0.001641814,0.0233925,0.00004979024,0.0003039677,0.03243608,0.02551866,0.000429848,0.0002603304,0.001607065,0.1703361,0.7408626],"study_design_scores_gemma":[0.007791676,0.002906365,0.8594744,0.0004231055,0.0009874728,0.001200383,0.05356083,0.004078206,0.0001060191,0.02402831,0.04412798,0.001315298],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9785506,0.00001437203,0.01817006,0.0002858046,0.001948618,0.0005753743,0.00001701857,0.00002173447,0.0004164281],"genre_scores_gemma":[0.9889009,0.00002078283,0.009457145,0.0002261328,0.0007074671,0.00001379297,7.603024e-7,0.00002625419,0.0006467465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8360819,"threshold_uncertainty_score":0.7997706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1281820078309743,"score_gpt":0.3802727481647573,"score_spread":0.252090740333783,"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."}}