{"id":"W4389923528","doi":"10.21449/ijate.1394194","title":"Language models in automated essay scoring: Insights for the Turkish language","year":2023,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Turkish; Transformative learning; Computer science; Language model; Artificial intelligence; Natural language processing; Intersection (aeronautics); Transformer; Linguistics; Sociology; Engineering","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":[0.004112748,0.0004509258,0.0003452037,0.001449701,0.0005865339,0.003842706,0.0006441355,0.0005667455,0.001729318],"category_scores_gemma":[0.02496612,0.0002149431,0.0004169466,0.001279537,0.001041621,0.004149931,0.00136502,0.001147993,0.0006754607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001689797,"about_ca_system_score_gemma":0.001754807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007036024,"about_ca_topic_score_gemma":0.009395199,"domain_scores_codex":[0.9956204,0.003511669,0.0001372978,0.0002749255,0.0003478659,0.0001077991],"domain_scores_gemma":[0.9829196,0.01380828,0.001023424,0.0006548136,0.001362255,0.0002317357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005091795,0.0003094597,0.0523949,0.0004619691,0.0001404223,0.0011472,0.01600488,0.1636373,0.006191288,0.339713,0.005529005,0.4139614],"study_design_scores_gemma":[0.00002213781,0.0001222591,0.01040009,0.0001166214,0.00004699943,0.0004193832,0.004952389,0.7994181,0.001692054,0.1688572,0.01387744,0.00007542494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5608739,0.001829608,0.4081589,0.005322307,0.00009407947,0.000155569,0.0004805939,0.0005325463,0.02255251],"genre_scores_gemma":[0.9667667,0.0002277538,0.03166266,0.00007667572,0.00003046653,0.00004538659,0.0001372546,0.00004370776,0.001009474],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007036024,"threshold_uncertainty_score":0.02175057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0407797704534206,"score_gpt":0.3934933832112348,"score_spread":0.3527136127578142,"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."}}