{"id":"W2230811337","doi":"10.5430/elr.v4n4p58","title":"Comparison of Inter-rater Reliability of Human and Computer Prosodic Annotation Using Brazil’s Prosody Model","year":2015,"lang":"en","type":"article","venue":"English Linguistics Research","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Kappa; Prosody; Reliability (semiconductor); Correlation; Syllable; Population; Inter-rater reliability; Tone (literature); Annotation; Pearson product-moment correlation coefficient; Statistics; Cohen's kappa; Computer science; Speech recognition; Mathematics; Natural language processing; Artificial intelligence; Linguistics; Rating scale; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003109552,0.000134686,0.0003997774,0.0003451435,0.0001178429,0.00004156418,0.0003391081,0.0002202319,0.00003312084],"category_scores_gemma":[0.006208851,0.0001292113,0.00003856782,0.0003597195,0.0009703119,0.00002856089,0.0003745599,0.000800011,0.000006529886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006862861,"about_ca_system_score_gemma":0.0002215268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004575499,"about_ca_topic_score_gemma":0.0000272892,"domain_scores_codex":[0.9973215,0.0006042589,0.0006085557,0.0004201213,0.0005754647,0.0004700518],"domain_scores_gemma":[0.990821,0.0003603969,0.0001442371,0.0005572746,0.007925042,0.0001920278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001252413,0.003346062,0.7135896,0.001082488,0.0001778578,0.00002794669,0.2160865,0.004256477,0.009087231,0.03005009,0.01942405,0.001619257],"study_design_scores_gemma":[0.004285738,0.004632841,0.04715288,0.0003042874,0.00005591522,0.0000038265,0.004563698,0.875185,0.01961914,0.04126234,0.00231427,0.0006201239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867028,0.0001755113,0.001456445,0.00001384508,0.0007484958,0.0004950369,0.00004049298,0.00002102063,0.01034635],"genre_scores_gemma":[0.9961264,0.000003225122,0.002975957,0.000005919487,0.0005536057,0.00001991691,0.00002228736,0.00002539954,0.0002672938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8709285,"threshold_uncertainty_score":0.7433024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2703584596292362,"score_gpt":0.5320530570359621,"score_spread":0.2616945974067259,"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."}}