{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001050738,0.0008729721,0.0006526597,0.00313836,0.0002231813,0.0008393172,0.001005101,0.0006137836,0.001022866],"category_scores_gemma":[0.002687098,0.0003011126,0.001452014,0.002383124,0.0001880293,0.001272631,0.0008652115,0.000730044,0.001229284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004701097,"about_ca_system_score_gemma":0.0006389374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006123237,"about_ca_topic_score_gemma":0.009533457,"domain_scores_codex":[0.999403,0.0001203445,0.00005579829,0.0002196365,0.0001229381,0.00007831015],"domain_scores_gemma":[0.9989873,0.0003889551,0.0001476431,0.0001682271,0.0002555339,0.00005235593],"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":[0.0004084647,0.0006338488,0.09211027,0.0002940097,0.000397754,0.0005172023,0.0003702302,0.2750942,0.018526,0.005022388,0.01345579,0.5931697],"study_design_scores_gemma":[0.000003927278,0.00002985034,0.004157341,0.000004934815,0.00001814923,0.0000342628,0.00002981279,0.9921565,0.001375696,0.001251241,0.0009286863,0.000009619899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1836069,0.0006053453,0.8027623,0.0006122952,0.0001545063,0.0002020859,0.004978412,0.005258205,0.001819844],"genre_scores_gemma":[0.8233629,0.0003457711,0.1610228,0.000142397,0.000135884,0.0003651046,0.01140021,0.0001262794,0.003098714],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006123237,"threshold_uncertainty_score":0.0121752,"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."}}