{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002569665,0.0004372194,0.0001762161,0.001095309,0.0001458284,0.0009243711,0.0002578198,0.0003226456,0.001450249],"category_scores_gemma":[0.01425409,0.0001858557,0.0002280774,0.0005280212,0.00042485,0.0008918585,0.0006709145,0.0004014818,0.0005052774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001929617,"about_ca_system_score_gemma":0.0003607056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002729662,"about_ca_topic_score_gemma":0.005503613,"domain_scores_codex":[0.9985647,0.0006664735,0.0001005789,0.0003155547,0.0002777192,0.00007500731],"domain_scores_gemma":[0.9854544,0.01057117,0.001808324,0.0008334965,0.001050678,0.0002818551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002080303,0.0001045308,0.9256448,0.00007718473,0.00006916486,0.0001106648,0.001715561,0.001815344,0.009085123,0.0003311131,0.0001996513,0.06063884],"study_design_scores_gemma":[0.000007434216,0.0003299839,0.9814379,0.00002580737,0.00002644402,0.0002609379,0.001108658,0.009700258,0.006009785,0.0003907523,0.0006737213,0.00002837268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9932673,0.00006910231,0.004340968,0.0000281821,0.000004894812,0.00001860656,0.0002773609,0.00003845007,0.001955219],"genre_scores_gemma":[0.9952027,0.00004208675,0.004228787,0.000007924007,0.000003333684,0.00002561538,0.0002126397,0.000008314098,0.0002685625],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002729662,"threshold_uncertainty_score":0.0135898,"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."}}