{"id":"W2325923846","doi":"10.5539/elt.v9n5p98","title":"Comparison of Native and Non-native English Language Teachers’ Evaluation of EFL Learners’ Speaking Skills: Conflicting or Identical Rating Behaviour?","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Fluency; Psychology; First language; Language proficiency; Mathematics education; Vocabulary; Pearson product-moment correlation coefficient; Test (biology); Rating scale; Significant difference; Linguistics; Developmental psychology; Statistics; Mathematics","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":[0.01140873,0.0002120515,0.0003603825,0.001108729,0.0003303646,0.0008957697,0.0003764126,0.0004066006,0.0007791842],"category_scores_gemma":[0.03844482,0.0002113827,0.0003523038,0.0004702731,0.0007218582,0.0007146431,0.001161152,0.0003082525,0.0004327325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001842893,"about_ca_system_score_gemma":0.0002848273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001058087,"about_ca_topic_score_gemma":0.001754226,"domain_scores_codex":[0.989714,0.004769861,0.001851834,0.0008668108,0.002449646,0.0003477785],"domain_scores_gemma":[0.9722411,0.01479756,0.003792183,0.001956838,0.006104208,0.00110814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000659498,0.0001791504,0.8451427,0.0003012976,0.0002503745,0.0005343328,0.05966347,0.0001750954,0.02076041,0.0001771367,0.000399267,0.07175726],"study_design_scores_gemma":[0.00001776916,0.0007727612,0.9611692,0.00006778449,0.00005363718,0.0009677237,0.03118042,0.0006403917,0.003804874,0.000170278,0.001115341,0.00003988715],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.997565,0.0001625368,0.0007388975,0.00002731923,0.0000148093,0.00001879211,0.00002051458,0.00001075603,0.001441277],"genre_scores_gemma":[0.9986585,0.00007628174,0.0006817143,0.0000242172,0.000006413488,0.00002861215,0.00004856964,0.000007238356,0.0004684413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01140873,"threshold_uncertainty_score":0.06033587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04161681684629527,"score_gpt":0.364497786540308,"score_spread":0.3228809696940127,"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."}}