{"id":"W1851653583","doi":"10.1007/s10994-015-5535-7","title":"Learning to identify relevant studies for systematic reviews using random forest and external information","year":2015,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Random forest; Computer science; Heuristics; Machine learning; Classifier (UML); Artificial intelligence; Cluster analysis; Systematic review; Class (philosophy); Recall; USable; Task (project management); Data mining; Information retrieval; Natural language processing; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002732664,0.0001553762,0.0004358626,0.0001994585,0.0002498922,0.0003484708,0.0003543269,0.00003739154,4.799728e-7],"category_scores_gemma":[0.006535427,0.0001238257,0.00004760855,0.0002327659,0.00002059163,0.001346337,0.0003040576,0.0001844383,0.00002349649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001006142,"about_ca_system_score_gemma":0.00002124252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002384685,"about_ca_topic_score_gemma":0.000005902542,"domain_scores_codex":[0.9984247,0.0002987865,0.0006055691,0.000221158,0.0002426863,0.0002071118],"domain_scores_gemma":[0.9985757,0.0003375062,0.000471889,0.0002833073,0.0002336652,0.00009787907],"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":[0.0007638857,0.0001882387,0.07189763,0.1094768,0.0005691663,0.00003425526,0.1742913,0.2071294,0.03541701,0.05300159,0.007588075,0.3396426],"study_design_scores_gemma":[0.001008604,0.0002105279,0.0004560792,0.003750595,0.00003047487,0.00004902403,0.0005741933,0.978644,0.0002433031,0.001650502,0.0131114,0.0002712948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01411717,0.001569202,0.9822214,0.0002332765,0.0001261577,0.001437122,0.000001187271,0.000261049,0.00003346516],"genre_scores_gemma":[0.5247203,0.0003068684,0.4735105,0.0003923212,0.00009509682,0.0005639467,0.00002505232,0.00002426578,0.0003616664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7715146,"threshold_uncertainty_score":0.7823988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09096737967275106,"score_gpt":0.3815705795832492,"score_spread":0.2906031999104981,"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."}}