{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003822156,0.0009755284,0.000522297,0.001455464,0.0005492886,0.002087131,0.001284197,0.001534618,0.004903363],"category_scores_gemma":[0.02099829,0.0003030456,0.0007015988,0.0007310549,0.0006293401,0.002436706,0.0009945612,0.00172464,0.00197495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001279126,"about_ca_system_score_gemma":0.001589429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006204411,"about_ca_topic_score_gemma":0.007297394,"domain_scores_codex":[0.9966826,0.001563781,0.0002376708,0.0008438542,0.0004868454,0.0001852087],"domain_scores_gemma":[0.9904832,0.006504614,0.0003736688,0.0006434181,0.001769999,0.0002251378],"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":[0.000618712,0.000984295,0.01042961,0.000435882,0.0001040789,0.0002772688,0.00130492,0.06941056,0.02317803,0.006986966,0.006072301,0.8801974],"study_design_scores_gemma":[0.00006934408,0.0003021197,0.004264066,0.00004890444,0.00003088014,0.00009971874,0.0003021693,0.9488851,0.0303388,0.01015313,0.005470116,0.00003574338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1868436,0.0004027942,0.7972554,0.0007000932,0.0001581033,0.0007131973,0.0006151848,0.007957877,0.005353734],"genre_scores_gemma":[0.448173,0.00009932902,0.5463386,0.000179499,0.00004371074,0.0004065977,0.001438446,0.000172313,0.003148484],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006204411,"threshold_uncertainty_score":0.02021378,"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."}}