{"id":"W4285021069","doi":"10.2139/ssrn.4088821","title":"Ups and Downs: How to Shape an Audience's Sentiment","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Advertising; Sentiment analysis; Psychology; Political science; Computer science; Business; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00204349,0.0003293991,0.0003305959,0.0005396936,0.00100664,0.004723,0.000400167,0.001793504,0.02088379],"category_scores_gemma":[0.01490535,0.0002309716,0.0002745672,0.0003584488,0.001074296,0.004010792,0.001563186,0.001804748,0.003597805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008149748,"about_ca_system_score_gemma":0.0003287572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008207306,"about_ca_topic_score_gemma":0.001023486,"domain_scores_codex":[0.9988305,0.0005627878,0.00003542668,0.0001424194,0.0002637783,0.0001650277],"domain_scores_gemma":[0.9959536,0.002159507,0.0004003206,0.0001619891,0.0007045233,0.0006201162],"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":[0.002936446,0.000866943,0.105392,0.0009828457,0.0003309771,0.001701366,0.03805831,0.006618375,0.06584629,0.2884157,0.1257588,0.3630921],"study_design_scores_gemma":[0.0004876307,0.001296436,0.1702399,0.0005949139,0.0006107548,0.0007369091,0.06189545,0.05875225,0.01462091,0.4366699,0.2537691,0.0003258741],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5320038,0.0008344523,0.01616899,0.02179478,0.001465142,0.0001044124,0.0003215527,0.000237439,0.4270695],"genre_scores_gemma":[0.9874344,0.0001624596,0.001255237,0.001213824,0.0003269261,0.00002815371,0.00004872622,0.0001116401,0.00941861],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02088379,"threshold_uncertainty_score":0.06986326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0590276298022419,"score_gpt":0.3580510354677922,"score_spread":0.2990234056655503,"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."}}