{"id":"W2969546362","doi":"10.1177/0894439319869210","title":"Automatic Classification of Open-Ended Questions: Check-All-That-Apply Questions","year":2019,"lang":"en","type":"article","venue":"Social Science Computer Review","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Computer science; Bivariate analysis; Code (set theory); Classifier (UML); Artificial intelligence; Natural language processing; Open data; Relevance (law); Information retrieval; Machine learning; Set (abstract data type); World Wide Web","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":[0.00155834,0.0001826133,0.0004298452,0.0002134529,0.0002787214,0.0005171794,0.004901088,0.00007759828,0.0000501028],"category_scores_gemma":[0.000111837,0.000160839,0.000114471,0.002365608,0.0004653615,0.002184688,0.001206583,0.0001730283,0.0002084147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001710382,"about_ca_system_score_gemma":0.0004157811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002224796,"about_ca_topic_score_gemma":0.000001839413,"domain_scores_codex":[0.9976001,0.0001413326,0.0005611209,0.0006580826,0.0006878664,0.0003515259],"domain_scores_gemma":[0.9979652,0.00007697156,0.0005531769,0.001019737,0.000296576,0.00008833603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[2.807831e-7,0.00007568184,0.0002579573,0.0002315838,0.00000656065,2.751652e-7,0.000148266,6.519937e-7,0.001100378,0.6809048,0.002970017,0.3143036],"study_design_scores_gemma":[0.001728706,0.00063793,0.3086741,0.008662897,0.000178823,0.00005449386,0.0004495504,0.1380719,0.003009873,0.1452256,0.3907124,0.002593685],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01549001,0.01810074,0.8412049,0.07102908,0.003595465,0.008804062,0.00001496677,0.005577567,0.03618315],"genre_scores_gemma":[0.8972406,0.004035471,0.09625803,0.001874678,0.00006743162,0.0002548023,0.000008826033,0.00001874797,0.0002414248],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8817506,"threshold_uncertainty_score":0.9107523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07185242578354825,"score_gpt":0.3688104459454661,"score_spread":0.2969580201619179,"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."}}