{"id":"W3159955930","doi":"10.24908/pceea.vi0.13741","title":"USING MACHINE LEARNING AS A TOOL TO HELP GUIDE UNDECLARED/UNDECIDED FIRST-YEAR ENGINEERING STUDENTS TOWARDS A DISCIPLINE","year":2019,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorization; Machine learning; Class (philosophy); Artificial intelligence; Decision tree; Classifier (UML); Computer science; Logistic regression; Random forest; Engineering education; Mathematics education; Psychology; Engineering; Engineering management","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"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":[0.003002842,0.0005944901,0.0004892792,0.002544188,0.0006215752,0.00198916,0.0007837476,0.0006520349,0.008175381],"category_scores_gemma":[0.01295821,0.0002038568,0.0002406055,0.00185957,0.0003331254,0.001147026,0.001054815,0.0006496722,0.005101161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008502493,"about_ca_system_score_gemma":0.001253025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003731136,"about_ca_topic_score_gemma":0.01136684,"domain_scores_codex":[0.9979231,0.001003803,0.0001262051,0.000304709,0.0005173797,0.0001248326],"domain_scores_gemma":[0.9882658,0.008248682,0.0007478308,0.0006939038,0.001450747,0.0005930442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002639607,0.001117874,0.05004275,0.0003762477,0.00003152131,0.000285858,0.005194033,0.004571827,0.01001192,0.002227882,0.07365671,0.8522193],"study_design_scores_gemma":[0.0003290671,0.002912251,0.1543307,0.0007579607,0.00009467856,0.0009092206,0.02864073,0.3723939,0.06329683,0.02173276,0.3541934,0.0004085131],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.476824,0.0005897281,0.4282535,0.005182296,0.0003729216,0.001585266,0.009333309,0.03300131,0.04485764],"genre_scores_gemma":[0.4735039,0.0003290913,0.4954951,0.00065048,0.00005965774,0.001060494,0.007181091,0.0003625139,0.02135766],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008175381,"threshold_uncertainty_score":0.02734935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01005706863665028,"score_gpt":0.2578494121216062,"score_spread":0.2477923434849559,"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."}}