{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01440487,0.001469915,0.001378068,0.003763702,0.001033696,0.001708331,0.002518164,0.002740496,0.008999622],"category_scores_gemma":[0.07551589,0.0004353547,0.001018257,0.002091517,0.0008921368,0.002611509,0.003856933,0.002451804,0.007953134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001186338,"about_ca_system_score_gemma":0.001684258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001943423,"about_ca_topic_score_gemma":0.002896647,"domain_scores_codex":[0.9807648,0.01076301,0.00131253,0.002937728,0.003377155,0.0008447792],"domain_scores_gemma":[0.8996104,0.07050169,0.006695175,0.008708668,0.01267115,0.001812881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002784077,0.002671615,0.06015381,0.001949691,0.0001616112,0.0002870409,0.004290761,0.006507992,0.02129761,0.005232276,0.05827988,0.8363835],"study_design_scores_gemma":[0.0009323637,0.00184452,0.1582113,0.00097077,0.0001629088,0.0008518634,0.007535171,0.5871253,0.1004534,0.038297,0.103169,0.0004464069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4548325,0.0009763283,0.4643982,0.001798678,0.001142693,0.007841569,0.0144823,0.03795178,0.01657595],"genre_scores_gemma":[0.545772,0.0001811941,0.4110133,0.0009730368,0.0002831869,0.006373592,0.02353868,0.001218065,0.01064698],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01440487,"threshold_uncertainty_score":0.07618117,"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."}}