{"id":"W2993353296","doi":"10.5539/elt.v13n1p18","title":"Comparison of Automatic and Expert Teachers’ Rating of Computerized English Listening-Speaking Test","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Active listening; Rasch model; Test (biology); Reliability (semiconductor); Inter-rater reliability; Rating scale; Mathematics education; Applied psychology; Developmental psychology; Communication","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007411029,0.0002674662,0.0002994858,0.001413563,0.0002078302,0.0004435595,0.0002980212,0.0002618733,0.001185758],"category_scores_gemma":[0.03327499,0.0001471706,0.000259646,0.000482141,0.0003470848,0.0004980611,0.0005818764,0.000248263,0.0003491462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002933331,"about_ca_system_score_gemma":0.0002425726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001434026,"about_ca_topic_score_gemma":0.003291152,"domain_scores_codex":[0.9917107,0.003446666,0.00105382,0.001026794,0.002515923,0.0002460188],"domain_scores_gemma":[0.9699039,0.01376372,0.00378369,0.002933534,0.008826646,0.0007884814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001232895,0.0002968381,0.7959883,0.0001961329,0.0002769135,0.0002090416,0.01399077,0.001983492,0.02647218,0.0003275943,0.001065381,0.1579605],"study_design_scores_gemma":[0.00003675515,0.0008688133,0.9874547,0.00001586999,0.00004209629,0.0002307838,0.00211207,0.004504693,0.003871224,0.00008458414,0.0007381199,0.00004035535],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959928,0.00003232941,0.002362953,0.00001282233,0.000008939825,0.00003603368,0.00005772659,0.00003978121,0.001456642],"genre_scores_gemma":[0.9977841,0.00002409137,0.001301207,0.00001108536,0.000007254149,0.00003549591,0.0001289418,0.00001102456,0.0006967371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007411029,"threshold_uncertainty_score":0.03919375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0112248277917318,"score_gpt":0.3145122398373942,"score_spread":0.3032874120456624,"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."}}