{"id":"W3193405709","doi":"10.1080/10584609.2021.1952497","title":"The Automatic Analysis of Emotion in Political Speech Based on Transcripts","year":2021,"lang":"en","type":"article","venue":"Political Communication","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Sentiment analysis; Computer science; Emotion detection; Natural language processing; Artificial intelligence; Word (group theory); Politics; Emotion recognition; Linguistics; Speech recognition","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.001835718,0.0006222504,0.0002818577,0.002402555,0.0004865837,0.001113074,0.0003400871,0.0004120227,0.003182776],"category_scores_gemma":[0.01098497,0.0001841417,0.0004223708,0.001821706,0.0005000708,0.001353879,0.001023491,0.0007497543,0.004022772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003506607,"about_ca_system_score_gemma":0.0005045841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001277957,"about_ca_topic_score_gemma":0.00166346,"domain_scores_codex":[0.997668,0.001196089,0.0001987163,0.0003403848,0.0004543747,0.0001425081],"domain_scores_gemma":[0.993093,0.003189746,0.0008943024,0.0006935084,0.00199756,0.0001319254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008946913,0.0002149274,0.04266138,0.001606574,0.0001154906,0.0007823886,0.00799733,0.005283093,0.1671282,0.009024482,0.05144919,0.7128423],"study_design_scores_gemma":[0.0001882103,0.00097564,0.2320434,0.0009915618,0.0003147538,0.001904103,0.02529381,0.2689165,0.1977952,0.0404448,0.2307677,0.0003644497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5158718,0.0009668454,0.4070486,0.001545971,0.001048887,0.00132039,0.04015794,0.004915784,0.02712363],"genre_scores_gemma":[0.7384096,0.0007402572,0.2050608,0.0001597379,0.0004257794,0.001406553,0.04494521,0.0004775036,0.008374576],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003182776,"threshold_uncertainty_score":0.01064742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03438306487592343,"score_gpt":0.3140308064692799,"score_spread":0.2796477415933565,"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."}}