{"id":"W4200196734","doi":"10.5539/elt.v15n1p16","title":"Establishing an Operational Model of Rating Scale Construction for English Writing Assessment","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Education of the People's Republic of China","keywords":"Writing assessment; Judgement; Rating scale; Psychology; Scale (ratio); Grading (engineering); Mathematics education; Weighting; Construct (python library); Likert scale; Computer science","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":[0.08148102,0.001475464,0.001213806,0.005183247,0.001865336,0.005273687,0.00274056,0.001653399,0.002500362],"category_scores_gemma":[0.1574969,0.0009071602,0.001930914,0.005199488,0.004957235,0.007760631,0.002964112,0.003036469,0.001683257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004363892,"about_ca_system_score_gemma":0.00615147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002878997,"about_ca_topic_score_gemma":0.002590101,"domain_scores_codex":[0.9085511,0.06178818,0.008984158,0.006028578,0.01341074,0.001237179],"domain_scores_gemma":[0.872402,0.0730126,0.009151216,0.007850235,0.03646327,0.001120657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002369234,0.0006846756,0.07581175,0.00176967,0.0003809039,0.0003048318,0.02851864,0.02471923,0.006324794,0.4618797,0.01297883,0.38639],"study_design_scores_gemma":[0.0003767188,0.002248199,0.07121659,0.002339804,0.0004163802,0.0008837823,0.02340046,0.4382861,0.00762727,0.3867839,0.0655997,0.0008210761],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01807361,0.000145663,0.9674258,0.0008796233,0.0001125969,0.003213635,0.0002349317,0.000408295,0.009505955],"genre_scores_gemma":[0.160144,0.0001260926,0.8321992,0.0001334507,0.00003783428,0.006249567,0.0004032285,0.00006943012,0.0006371288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08148102,"threshold_uncertainty_score":0.430918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01405824346634783,"score_gpt":0.3124344167760603,"score_spread":0.2983761733097125,"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."}}