{"id":"W2523536876","doi":"10.5539/ijel.v6n5p54","title":"The Effect of Using Automated Essay Evaluation on ESL Undergraduate Students’ Writing Skill","year":2016,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Grammar; Computer science; Mathematics education; Test (biology); Software; Second language writing; Relation (database); Academic writing; Artificial intelligence; Natural language processing; Psychology; Second language; Linguistics; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004346386,0.00009506929,0.0001583476,0.0001163805,0.0002068608,0.000162601,0.0006796363,0.00005420263,0.00002713643],"category_scores_gemma":[0.08951544,0.00005572595,0.0001141572,0.000106899,0.0001438472,0.00007944053,0.0000606005,0.000122318,0.000002909105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004548923,"about_ca_system_score_gemma":0.0002298299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002515029,"about_ca_topic_score_gemma":0.00002141402,"domain_scores_codex":[0.9964957,0.0004469434,0.0005225205,0.00008907583,0.002284321,0.0001614683],"domain_scores_gemma":[0.9840978,0.00236052,0.000717175,0.00008114766,0.0126869,0.00005643828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001070217,0.0004916848,0.8714366,0.00002312732,0.00204165,0.00005528543,0.01388824,0.002313575,0.0005497853,0.0742238,0.00830557,0.02560044],"study_design_scores_gemma":[0.05108509,0.005941637,0.3652773,0.009251968,0.003413511,0.00001022036,0.02962585,0.02000767,0.01394006,0.03930961,0.4594546,0.002682417],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9419203,0.0001026385,0.000210216,0.0002486671,0.02367403,0.0002332683,0.000008671441,0.00004460038,0.03355756],"genre_scores_gemma":[0.9929925,0.0001036525,0.0001626601,0.00001847768,0.006602852,0.000001360883,0.000001034817,0.000009840178,0.0001076759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5061593,"threshold_uncertainty_score":0.9181539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02576910350022154,"score_gpt":0.4149989833821516,"score_spread":0.3892298798819301,"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."}}