{"id":"W4205974171","doi":"10.1080/0969594x.2021.1999209","title":"Investigating the potential of NLP-driven linguistic and acoustic features for predicting human scores of children’s oral language proficiency","year":2021,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Reading and Literacy Development","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Storytelling; Vocabulary; Grammar; Literacy; Psychology; Computer science; Linguistics; Natural language processing; Artificial intelligence; Narrative; Pedagogy","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":[0.0008070465,0.00009726204,0.0001484744,0.0001125002,0.0001501834,0.00005010625,0.00009298134,0.00005176008,0.00001008149],"category_scores_gemma":[0.003451327,0.00008042021,0.00002165492,0.0001855934,0.0001021039,0.0001086908,0.0000652289,0.0001812937,1.598152e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003659694,"about_ca_system_score_gemma":0.0006446757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001498436,"about_ca_topic_score_gemma":0.00007433668,"domain_scores_codex":[0.9988071,0.0003189886,0.0003692979,0.0002178448,0.000131146,0.0001556334],"domain_scores_gemma":[0.9980178,0.001194055,0.0004003185,0.000181843,0.000163752,0.00004221179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000686478,0.001346671,0.5339083,0.000599134,0.0002595182,0.000004339291,0.1460677,0.0004407376,0.01841116,0.2774741,0.0002204195,0.02119933],"study_design_scores_gemma":[0.0004071127,0.00009694669,0.9744487,0.000178791,0.0001000248,0.0001134267,0.02246737,0.0002154485,0.0004799497,0.0009406016,0.0004464948,0.0001051192],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926202,0.0007271887,0.0001722779,0.001572783,0.000241093,0.0003647325,0.00001821025,0.000009497217,0.004273991],"genre_scores_gemma":[0.9892986,0.0000453277,0.009508324,0.0002790754,0.0002013419,0.000083352,0.00005214135,0.00001002797,0.0005217761],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4405404,"threshold_uncertainty_score":0.413181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03072020722652336,"score_gpt":0.4230499314041326,"score_spread":0.3923297241776092,"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."}}