{"id":"W4408618891","doi":"10.1016/j.trpro.2025.03.056","title":"Social Media as a Market Prophecy: Leveraging ML Algorithms for Predicting Market Trends and Demand","year":2025,"lang":"en","type":"article","venue":"Transportation research procedia","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"World Anti-Doping Agency","funders":"","keywords":"Social media; Supply and demand; Computer science; On demand; Economics; Algorithm; Business; Microeconomics; World Wide Web; Multimedia","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.005398001,0.0001655095,0.0002637667,0.0004177038,0.001629995,0.0002883929,0.0002563088,0.0002204191,0.0001523226],"category_scores_gemma":[0.003899828,0.0001744227,0.00009157075,0.001215177,0.0006465716,0.00037959,0.00001501616,0.0003684047,0.00000267418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001143866,"about_ca_system_score_gemma":0.0007945027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00046951,"about_ca_topic_score_gemma":0.002879457,"domain_scores_codex":[0.99699,0.0003441684,0.0003719477,0.0004841234,0.001021847,0.0007879387],"domain_scores_gemma":[0.9968756,0.002102537,0.00008528999,0.00008720725,0.0006139295,0.0002354774],"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":[0.001065551,0.0002611502,0.05808593,0.001158771,0.000190021,0.00003066246,0.2262723,0.000001403789,0.00005889305,0.0599128,0.1119289,0.5410336],"study_design_scores_gemma":[0.00359427,0.0002032298,0.6997592,0.0005984738,0.0001378551,6.007276e-7,0.07466277,0.0008773183,0.000101739,0.06676836,0.1525623,0.0007338625],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5431173,0.0006206863,0.000640169,0.01644601,0.0008514968,0.002364806,0.0002080268,0.0007777058,0.4349738],"genre_scores_gemma":[0.981264,0.0001821147,0.0006329369,0.0000892704,0.0006440787,0.0005180893,0.00005053197,0.00003361013,0.01658534],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6416733,"threshold_uncertainty_score":0.9996697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06853170726011798,"score_gpt":0.4104725822551354,"score_spread":0.3419408749950174,"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."}}