{"id":"W3010385440","doi":"10.48550/arxiv.2003.03645","title":"Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Affect (linguistics); Conversation; Dilemma; Property (philosophy); Computer science; Control (management); Probabilistic logic; Human–computer interaction; Psychology; Cognitive psychology; Cognitive science; Artificial intelligence; Communication; Epistemology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007896138,0.0002856238,0.0003911067,0.0002939775,0.0001354288,0.0001444377,0.001327801,0.0002261261,0.000009699942],"category_scores_gemma":[0.0002532361,0.0003408476,0.0001760348,0.0003782609,0.00006222025,0.0003104365,0.001264327,0.000366354,0.00001562372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002524547,"about_ca_system_score_gemma":0.0003852454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001390033,"about_ca_topic_score_gemma":0.00005163319,"domain_scores_codex":[0.9971873,0.0009808285,0.0002616438,0.00113059,0.0001142178,0.0003254756],"domain_scores_gemma":[0.9982862,0.000507084,0.0002221542,0.0007757179,0.00008850844,0.0001203331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007233359,0.0000284235,0.003155049,0.00003901493,0.000051121,0.0004882976,0.0004027955,0.8399951,0.001810936,0.153549,0.000007704102,0.0004002879],"study_design_scores_gemma":[0.0005816103,0.00002445215,0.00106707,0.0001051623,0.00003061712,0.000004208648,0.00003209044,0.9348557,0.0001154055,0.0628611,0.000009405564,0.0003131891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4215319,0.00005758956,0.5775782,0.0001124598,0.0002744409,0.0001884474,0.000008033628,0.0001197796,0.000129017],"genre_scores_gemma":[0.9832633,0.00002094617,0.01604063,0.0003530983,0.0001703516,8.431336e-7,0.000006923016,0.00001689772,0.000127021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5617313,"threshold_uncertainty_score":0.9999043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.128191363884565,"score_gpt":0.2146575161884615,"score_spread":0.08646615230389654,"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."}}