{"id":"W2941057185","doi":"10.3389/fpsyg.2019.00825","title":"Multiple-Choice Item Distractor Development Using Topic Modeling Approaches","year":2019,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Topic Modeling","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Task (project management); Multiple choice; Latent Dirichlet allocation; Test (biology); Quality (philosophy); Process (computing); Cognitive psychology; Natural language processing; Item response theory; Artificial intelligence; Topic model; Computer science; Mathematics education; Linguistics; Psychometrics; Developmental psychology","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":[0.0002527168,0.0001654016,0.0002544522,0.0002047599,0.00005041501,0.00004443893,0.0008266501,0.0001557794,0.000006457738],"category_scores_gemma":[0.00008225761,0.0001711296,0.00004354018,0.0002146854,0.00002082722,0.0003002383,0.0001584342,0.0002584891,0.0000171004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001194068,"about_ca_system_score_gemma":0.00006067547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002302664,"about_ca_topic_score_gemma":0.00001136499,"domain_scores_codex":[0.9982919,0.00006954592,0.0003830148,0.000675784,0.0001627036,0.0004170431],"domain_scores_gemma":[0.999075,0.00009193305,0.00007899168,0.000667251,0.0000202896,0.00006651749],"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":[0.00001511556,0.00012274,0.8245314,0.00003948223,0.00003354132,0.00001250681,0.001695448,0.02534157,0.0003228572,0.0008536298,0.0002071484,0.1468246],"study_design_scores_gemma":[0.0005843928,0.00001176736,0.01116927,0.00002223696,0.000001808171,0.000009098241,0.0000812271,0.984266,0.00004153309,0.00138359,0.002221001,0.0002080249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4100887,0.0002048601,0.5865939,0.000119852,0.00212826,0.0001354648,2.514423e-7,0.00004579944,0.0006828918],"genre_scores_gemma":[0.5819655,0.000003618514,0.4177403,0.0001748758,0.00004970862,0.000008284702,0.000001635209,0.000007895709,0.00004822581],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9589245,"threshold_uncertainty_score":0.6978462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09783407409281254,"score_gpt":0.2976876296197643,"score_spread":0.1998535555269518,"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."}}