{"id":"W2981551119","doi":"10.1080/10494820.2019.1680391","title":"Using learning analytics to support students’ engineering design: the angle of prediction","year":2019,"lang":"en","type":"article","venue":"Interactive Learning Environments","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Science Foundation of Sri Lanka","keywords":"Computer science; Feature engineering; Task (project management); Machine learning; Artificial intelligence; Learning analytics; Analytics; Ranking (information retrieval); Process (computing); Curse of dimensionality; Feature selection; Feature (linguistics); Rank (graph theory); Data science; Deep learning; Engineering","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":[0.003129915,0.001944851,0.0008569921,0.002322441,0.0004063339,0.003508543,0.000974197,0.001326139,0.0017843],"category_scores_gemma":[0.02180416,0.0003429678,0.0005443318,0.001769125,0.0007697968,0.005296792,0.00133107,0.002901222,0.0007980749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000716959,"about_ca_system_score_gemma":0.001070368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002508438,"about_ca_topic_score_gemma":0.002547272,"domain_scores_codex":[0.9980515,0.0009433572,0.0001050371,0.0003062425,0.0004800973,0.0001137352],"domain_scores_gemma":[0.9813906,0.01421344,0.001401177,0.001129333,0.001403348,0.0004621156],"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":[0.0003488574,0.00156926,0.08704506,0.0005542046,0.0001566489,0.0001400267,0.001426738,0.1531215,0.003919843,0.01861838,0.00759563,0.7255039],"study_design_scores_gemma":[0.00002222621,0.0003025872,0.01193559,0.0002104357,0.00003942364,0.000060579,0.0007777767,0.9276773,0.004247291,0.04950615,0.005148113,0.00007253517],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1940462,0.002741595,0.7858365,0.005487932,0.0002076232,0.0002083013,0.0005554775,0.002224644,0.008691698],"genre_scores_gemma":[0.8848965,0.0012725,0.1116434,0.0002041193,0.000126529,0.0001078141,0.0005407264,0.00008297133,0.001125445],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003508543,"threshold_uncertainty_score":0.01655275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02218614371651277,"score_gpt":0.2881865424488955,"score_spread":0.2660003987323827,"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."}}