{"id":"W3040446934","doi":"10.1177/0265532220937830","title":"More efficient processes for creating automated essay scoring frameworks: A demonstration of two algorithms","year":2020,"lang":"en","type":"article","venue":"Language Testing","topic":"Topic Modeling","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Rubric; Artificial intelligence; Machine learning; Computer science; Support vector machine; Convolutional neural network; Feature engineering; Deep learning; Artificial neural network; Natural language processing; Meaning (existential); Feature (linguistics); Strengths and weaknesses; F1 score; Algorithm; Mathematics; Mathematics education; Linguistics; 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":[0.008945438,0.001384207,0.00104886,0.002867866,0.0006793856,0.003223549,0.002265602,0.001473953,0.005215978],"category_scores_gemma":[0.03084167,0.0006046362,0.0009189309,0.00137674,0.0008801701,0.004060037,0.003932704,0.002276634,0.003369427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001126093,"about_ca_system_score_gemma":0.001913853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0040064,"about_ca_topic_score_gemma":0.003722943,"domain_scores_codex":[0.9912093,0.003265555,0.0008352937,0.001474984,0.002880558,0.0003344095],"domain_scores_gemma":[0.9843061,0.005490905,0.0009894988,0.003672051,0.004896226,0.0006451946],"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":[0.0003645668,0.0004658359,0.005595087,0.0001998245,0.00009232007,0.000173118,0.0008095588,0.02525309,0.01872413,0.02787673,0.00933248,0.9111131],"study_design_scores_gemma":[0.00009948329,0.0002208056,0.004040509,0.00006183771,0.00003269862,0.0003489883,0.0003075796,0.9240695,0.0313393,0.02094692,0.01842266,0.0001096736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01761846,0.0001480532,0.9709029,0.0003394759,0.0001389826,0.0003537667,0.000182994,0.007318974,0.00299633],"genre_scores_gemma":[0.1304706,0.0001190297,0.864866,0.0000875427,0.00008666054,0.0003559971,0.000450898,0.000453288,0.003110036],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008945438,"threshold_uncertainty_score":0.04730856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0348837319221498,"score_gpt":0.309711483163347,"score_spread":0.2748277512411972,"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."}}