{"id":"W4251941390","doi":"10.1177/0265532220929918","title":"Automated scoring of junior and senior high essays using Coh-Metrix features: Implications for large-scale language testing","year":2020,"lang":"en","type":"article","venue":"Language Testing","topic":"Software Engineering Research","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of Alberta","funders":"","keywords":"Natural language processing; Artificial intelligence; Rating scale; Computer science; Scale (ratio); Quality (philosophy); Construct (python library); Psychology; Computational linguistics; Disadvantaged; Machine learning; Developmental psychology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005099743,0.0001834195,0.0002773508,0.0001726493,0.00020698,0.0001450411,0.0005523913,0.00007625024,0.000002406511],"category_scores_gemma":[0.01280623,0.0001876516,0.00003671898,0.001711649,0.00003180611,0.0002565515,0.0004246361,0.0002298309,0.000001665597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006699291,"about_ca_system_score_gemma":0.00009463333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002521761,"about_ca_topic_score_gemma":0.000007400031,"domain_scores_codex":[0.9984274,0.0000440952,0.0002874923,0.0004702182,0.0002178771,0.0005529008],"domain_scores_gemma":[0.9955913,0.00342109,0.0001453042,0.0004265477,0.0002128271,0.0002028593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000109954,0.0000819273,0.113956,0.001104267,0.0000600877,0.00007170271,0.03106241,0.00501727,0.8071012,0.0009538756,0.0001414415,0.04043881],"study_design_scores_gemma":[0.001025519,0.0001706915,0.1006129,0.0003204192,0.00002718051,0.0001053082,0.001706215,0.8777049,0.01778612,0.00008529035,0.00001038726,0.0004450818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7929544,0.0004436481,0.2043096,0.0001651695,0.00006152351,0.0003297323,0.00005130433,0.001643458,0.00004123371],"genre_scores_gemma":[0.6143281,3.807035e-7,0.3854439,0.0000633857,0.0000993271,0.00002344203,0.000005428649,0.00002625172,0.00000985091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8726876,"threshold_uncertainty_score":0.9955093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0384669575825602,"score_gpt":0.314934657209404,"score_spread":0.2764676996268438,"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."}}