{"id":"W3030494876","doi":"10.1177/0735633120927486","title":"Computer Science Meets Education: Natural Language Processing for Automatic Grading of Open-Ended Questions in eBooks","year":2020,"lang":"en","type":"article","venue":"Journal of Educational Computing Research","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Javna Agencija za Raziskovalno Dejavnost RS; Fulbright Association; University of South Florida","keywords":"Computer science; Grading (engineering); Artificial intelligence; Natural language processing; Inference; Reading comprehension; Set (abstract data type); Narrative; Reading (process); Mathematics education; Linguistics; Programming language; Mathematics","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":[0.003160006,0.00008643758,0.0002266773,0.0006618226,0.0003469779,0.0005264694,0.00204052,0.0000264025,0.000002959898],"category_scores_gemma":[0.001638813,0.00007792117,0.00005924219,0.001163655,0.000181784,0.0005390744,0.0004394223,0.0005290133,0.00000156239],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001631742,"about_ca_system_score_gemma":0.006174277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002137632,"about_ca_topic_score_gemma":0.000002548481,"domain_scores_codex":[0.9979487,0.0001722785,0.0005646804,0.0002497812,0.0007717199,0.0002928458],"domain_scores_gemma":[0.9967298,0.0009985755,0.000384832,0.0001668273,0.001550277,0.0001697018],"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":[0.0000453204,0.001306657,0.006234339,0.000874584,0.00005227615,0.000009907517,0.0301997,0.007966825,0.01099419,0.1277062,0.004498472,0.8101115],"study_design_scores_gemma":[0.0003738117,0.0002165856,0.009575392,0.000786578,0.000004954663,0.00005754636,0.0006617748,0.9810664,0.0006251304,0.006313919,0.0002058842,0.0001120381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8523583,0.001297631,0.05016939,0.09381539,0.000992322,0.00051969,0.000001641926,0.00002590489,0.0008197492],"genre_scores_gemma":[0.7795722,9.276045e-7,0.2197054,0.0001487553,0.0005042644,0.0000020469,0.00000103506,0.000005547215,0.00005981411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9730996,"threshold_uncertainty_score":0.9994598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07584755175589959,"score_gpt":0.4745538472965157,"score_spread":0.3987062955406161,"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."}}