{"id":"W4319779582","doi":"10.1109/icdmw58026.2022.00064","title":"Feature Extraction and Prediction of Combined Text and Survey Data using Two-Staged Modeling","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Data Mining Workshops (ICDMW)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Domain adaptation; Convolutional neural network; Feature extraction; Deep learning; Machine learning; Recurrent neural network; Artificial neural network; Pattern recognition (psychology); Data mining","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":[0.001868259,0.0001934972,0.0002318441,0.0002430618,0.0003099988,0.0002882537,0.002580191,0.00006406022,0.00008861937],"category_scores_gemma":[0.0002964028,0.0002179448,0.00001737643,0.0002751623,0.0000504841,0.001493676,0.003169682,0.0005506926,7.442474e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000864716,"about_ca_system_score_gemma":0.0001510315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002880954,"about_ca_topic_score_gemma":0.0001240191,"domain_scores_codex":[0.9973304,0.0002912477,0.0003792541,0.001043266,0.0007454492,0.0002103451],"domain_scores_gemma":[0.9975658,0.0003122538,0.0002828159,0.001602047,0.0001584204,0.00007866028],"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":[0.001534623,0.001015327,0.06124563,0.0001634709,0.001000145,0.0001547922,0.00643046,0.4044732,0.03111671,0.03045741,0.0148852,0.4475231],"study_design_scores_gemma":[0.0005926871,0.00005635921,0.001570595,0.00006551092,0.00001717441,0.00004420504,0.0004205944,0.9967074,0.00003142339,0.0001902497,0.000136184,0.0001675835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4547162,0.0001396841,0.5393416,0.0009809451,0.002000005,0.0002212985,0.002260003,0.00008394273,0.0002562881],"genre_scores_gemma":[0.9682125,0.00008237719,0.02930693,0.00009463139,0.0001035568,0.000009427947,0.001996087,0.00001594655,0.0001785697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5922343,"threshold_uncertainty_score":0.8887532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2961297511315246,"score_gpt":0.3718854319065857,"score_spread":0.07575568077506112,"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."}}