{"id":"W4230648055","doi":"10.32920/ryerson.14644251.v1","title":"The impact of sentiment analysis on decision outcomes - an empirical investigation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sentiment analysis; Computer science; Product (mathematics); Service (business); Quality (philosophy); Filter (signal processing); Star (game theory); Marketing; Artificial intelligence; Business; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01467297,0.0005228016,0.0007558604,0.0009312868,0.0005853385,0.001989924,0.0006956232,0.0007686591,0.00336691],"category_scores_gemma":[0.08629455,0.0002671273,0.001018509,0.0008428186,0.001282779,0.001459445,0.001030394,0.002329937,0.0006402322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00112842,"about_ca_system_score_gemma":0.0006821869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001010238,"about_ca_topic_score_gemma":0.000904053,"domain_scores_codex":[0.9893757,0.006050404,0.00072401,0.001036917,0.002335055,0.0004778555],"domain_scores_gemma":[0.7261854,0.2427297,0.01721332,0.003985932,0.007425305,0.002460209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01370184,0.02039571,0.7322085,0.003246877,0.001373051,0.001168033,0.01606991,0.01329662,0.02041999,0.004119737,0.003898986,0.1701007],"study_design_scores_gemma":[0.0004977707,0.01743641,0.9072526,0.0003707414,0.0009146485,0.0003579107,0.00845387,0.04648612,0.00970848,0.003738582,0.004591749,0.0001910903],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968184,0.0001104744,0.0008679346,0.00008194537,0.00001580335,0.0001834209,0.0001240562,0.000007152403,0.001790721],"genre_scores_gemma":[0.9971189,0.0001310828,0.001611087,0.00006111504,0.00002299893,0.0003287743,0.0002086059,0.00001148979,0.0005058458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01467297,"threshold_uncertainty_score":0.07759899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05895634017010145,"score_gpt":0.3930029664949308,"score_spread":0.3340466263248293,"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."}}