{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002309982,0.0001175483,0.0001689332,0.00004232086,0.0001169198,0.00009745584,0.0003680387,0.00006002286,0.000001162452],"category_scores_gemma":[0.002601815,0.0001135787,0.00003051833,0.0005957231,0.00001890998,0.0001700886,0.0001225902,0.0001566914,9.166187e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002445424,"about_ca_system_score_gemma":0.0001417599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006518512,"about_ca_topic_score_gemma":0.000002610978,"domain_scores_codex":[0.9989178,0.00002229097,0.0003065706,0.0003387753,0.0001801548,0.0002344434],"domain_scores_gemma":[0.9987445,0.0005921955,0.0001989598,0.0002060337,0.0001895798,0.00006876143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007934903,0.00009054314,0.008498736,0.001534831,0.0000353108,0.00004417334,0.07838282,0.6210707,0.06189445,0.005106845,0.00001136717,0.2233223],"study_design_scores_gemma":[0.0002342855,0.00004007664,0.0001509813,0.0003069196,0.000008587147,0.00000740604,0.00059788,0.9859968,0.01245269,0.0000868758,8.432411e-7,0.0001166918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2182092,0.0001881094,0.7799336,0.0002883697,0.00004923395,0.0002091117,0.000002442844,0.0008561254,0.0002638107],"genre_scores_gemma":[0.5445089,1.099434e-7,0.4552332,0.0001353325,0.00009661452,0.00001453082,0.000001620078,0.000007476328,0.000002146754],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3649261,"threshold_uncertainty_score":0.4631606,"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."}}