{"id":"W4386214112","doi":"10.1016/j.knosys.2023.110938","title":"Label correlation guided borderline oversampling for imbalanced multi-label data learning","year":2023,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Weighting; Computer science; Machine learning; Class (philosophy); Multi-label classification; Artificial intelligence; Decision boundary; Range (aeronautics); Code (set theory); Correlation; Data mining; Source code; Tree (set theory); Macro; Pattern recognition (psychology); Support vector machine; Mathematics","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":[0.006894197,0.001274496,0.002748831,0.001610104,0.002252872,0.002366107,0.003693632,0.002851966,0.002465938],"category_scores_gemma":[0.0146956,0.0006362825,0.001140453,0.001324851,0.001855447,0.002332123,0.00417709,0.004005997,0.000966037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001648618,"about_ca_system_score_gemma":0.002924199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006873553,"about_ca_topic_score_gemma":0.01217405,"domain_scores_codex":[0.9964511,0.001064253,0.0002074852,0.0009191212,0.0009042,0.0004537268],"domain_scores_gemma":[0.9921843,0.004005544,0.0004520572,0.00137614,0.001471473,0.0005104899],"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":[0.003115531,0.001546789,0.01609483,0.0003758334,0.000263726,0.0004456761,0.0008685146,0.1710227,0.01897667,0.0209995,0.02239667,0.7438935],"study_design_scores_gemma":[0.0000493495,0.0001039046,0.0006019576,0.00002138461,0.00002957766,0.00005232642,0.00009364399,0.9846676,0.003231801,0.009803217,0.001334026,0.00001107234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08972379,0.001074906,0.902404,0.0008544028,0.0003725568,0.0003130638,0.0004264225,0.0033166,0.001514327],"genre_scores_gemma":[0.6765198,0.0002089,0.3151559,0.0008989552,0.0003086053,0.0003302596,0.002832486,0.0004221294,0.003323001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006894197,"threshold_uncertainty_score":0.03646046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1748491315610552,"score_gpt":0.3773169973589758,"score_spread":0.2024678657979206,"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."}}