{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02200578,0.000703687,0.0005234812,0.001890332,0.0006181063,0.001886702,0.001137919,0.0005495879,0.001673234],"category_scores_gemma":[0.1303999,0.0002520036,0.0004401214,0.001925125,0.0007089208,0.002083595,0.001714188,0.001215067,0.0006363264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001110748,"about_ca_system_score_gemma":0.001674405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00415322,"about_ca_topic_score_gemma":0.009832878,"domain_scores_codex":[0.9826245,0.01114907,0.001145939,0.001377271,0.003304211,0.0003989929],"domain_scores_gemma":[0.8740447,0.0725709,0.01356838,0.01436639,0.02334865,0.002100986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000787052,0.0008156315,0.5155722,0.0002352969,0.0001439789,0.0001213795,0.003062134,0.01071243,0.00787936,0.002254873,0.006686268,0.4517294],"study_design_scores_gemma":[0.00013235,0.001726347,0.665396,0.0001627556,0.00006515012,0.000316762,0.003222946,0.2953317,0.01865038,0.006333066,0.008492175,0.0001705095],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9057022,0.0001547389,0.08502079,0.000737787,0.0000782409,0.0006546102,0.0009435304,0.00160238,0.005105739],"genre_scores_gemma":[0.9451553,0.00002860357,0.05261295,0.00005831062,0.00002943647,0.0003828008,0.0007025354,0.00008279576,0.000947226],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02200578,"threshold_uncertainty_score":0.1163791,"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."}}