{"id":"W4414969774","doi":"10.48550/arxiv.2510.03633","title":"Predicting Stock Price Movement with LLM-Enhanced Tweet Emotion Analysis","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Stock price; Stock (firearms); Sentiment analysis; Volatility (finance); Classifier (UML); Eye movement; Time series","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009398141,0.0006658579,0.001394209,0.001719319,0.0003949711,0.0004109548,0.002151203,0.0004491425,0.0006304168],"category_scores_gemma":[0.01046998,0.0005150546,0.0006327044,0.005026964,0.0001434647,0.000252631,0.002410494,0.001173466,0.00007763409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003943874,"about_ca_system_score_gemma":0.0004916583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003624,"about_ca_topic_score_gemma":0.0002596425,"domain_scores_codex":[0.9909765,0.001388584,0.001732977,0.002412434,0.002780288,0.000709223],"domain_scores_gemma":[0.9898809,0.003829622,0.001857731,0.00292536,0.001262305,0.0002441331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001305388,0.000133633,0.9479365,0.00005431991,0.001358116,0.000008420714,0.0009775603,0.02199652,0.0002027369,0.00002470279,0.0006457508,0.02653119],"study_design_scores_gemma":[0.0004914691,0.0001764783,0.9607629,0.0003261098,0.001290126,0.000001308464,0.0006159995,0.03000836,0.002011263,0.003153286,0.0005442381,0.0006184258],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6655971,0.00006968824,0.3143908,0.0002631469,0.0009811744,0.000712671,0.00006977844,0.0002075425,0.01770812],"genre_scores_gemma":[0.9509102,0.00001682067,0.03386848,0.0003553257,0.0003162147,0.0002001449,0.00005944067,0.00003843262,0.01423495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2853131,"threshold_uncertainty_score":0.9997301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1281331243977541,"score_gpt":0.3988583599284989,"score_spread":0.2707252355307448,"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."}}