{"id":"W3201077663","doi":"10.1007/s10462-021-10068-2","title":"An automated essay scoring systems: a systematic literature review","year":2021,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":466,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Grading (engineering); Cohesion (chemistry); Relevance (law); Artificial intelligence; Evaluation methods; Data science","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003069314,0.0004329942,0.001347622,0.0001203115,0.000290322,0.0008972443,0.001128041,0.0001157446,0.00004599305],"category_scores_gemma":[0.001115686,0.0003546097,0.0003272665,0.00218446,0.00003310304,0.001092225,0.0001972855,0.000436379,0.0009005141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001656855,"about_ca_system_score_gemma":0.0002910013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000207481,"about_ca_topic_score_gemma":0.00000476658,"domain_scores_codex":[0.9943165,0.001564589,0.001818751,0.0009713563,0.0007207641,0.0006080792],"domain_scores_gemma":[0.9960051,0.0002467959,0.0005909433,0.001824152,0.001071786,0.0002612524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[7.439358e-7,0.0001025713,0.000005414493,0.4973691,0.00006304394,0.000636528,0.0003921525,0.0003145262,0.0003927089,0.4885021,0.0003394174,0.01188172],"study_design_scores_gemma":[0.000009694628,0.00006883163,0.00000183782,0.9402957,0.0001214411,0.0008893764,0.0001192619,0.04452978,0.001524622,0.0003853621,0.0115186,0.0005354912],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001545034,0.7207227,0.2751441,0.0006024461,0.001135144,0.001134295,0.000002503042,0.0007914031,0.0004520032],"genre_scores_gemma":[0.02485321,0.9623144,0.006214062,0.003484051,0.0005156847,0.0005227937,0.00003588375,0.00007307353,0.001986887],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4881167,"threshold_uncertainty_score":0.9998906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05070367394269971,"score_gpt":0.3469837066823772,"score_spread":0.2962800327396775,"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."}}