{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03095992,0.001378987,0.007763783,0.01702374,0.0009596975,0.004178014,0.003798845,0.002281541,0.004062529],"category_scores_gemma":[0.1004118,0.001161882,0.005571404,0.01149013,0.001574879,0.004384035,0.002994222,0.001611146,0.0006507061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003233307,"about_ca_system_score_gemma":0.01598152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005014418,"about_ca_topic_score_gemma":0.01824266,"domain_scores_codex":[0.9726405,0.01067385,0.009409751,0.001916237,0.005064133,0.0002955766],"domain_scores_gemma":[0.9101601,0.06369889,0.01161603,0.001673333,0.01216163,0.0006900252],"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":[0.0004313559,0.0001285926,0.003926791,0.7374538,0.00943111,0.0001107198,0.000511479,0.00031506,0.0002776761,0.0004680298,0.00472138,0.242224],"study_design_scores_gemma":[0.0007193945,0.0007992567,0.01353697,0.8536056,0.08372382,0.000607087,0.001106427,0.0007844805,0.0005834319,0.001042053,0.04333518,0.0001564467],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002774685,0.9926935,0.001308536,0.0006224596,0.0002200845,0.0009526198,0.00074578,0.0000308462,0.0006514242],"genre_scores_gemma":[0.0460788,0.9412262,0.007871666,0.001236663,0.0002096376,0.001720484,0.001317391,0.00002515945,0.0003138997],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.03095992,"threshold_uncertainty_score":0.1637337,"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."}}