{"id":"W2169863116","doi":"10.1145/1557019.1557119","title":"Effective multi-label active learning for text classification","year":2009,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":159,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Simon Fraser University","keywords":"Computer science; Multi-label classification; Support vector machine; Labeled data; Reduction (mathematics); Artificial intelligence; Machine learning; Active learning (machine learning); Point (geometry); Semi-supervised learning; Data reduction; Data mining; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008279143,0.001715288,0.0024561,0.002838794,0.001305513,0.002792038,0.006549824,0.004035273,0.002327968],"category_scores_gemma":[0.01612554,0.0009666382,0.001548524,0.002573651,0.002242641,0.007726616,0.002993714,0.004497479,0.001361997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001321071,"about_ca_system_score_gemma":0.0009644994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000909741,"about_ca_topic_score_gemma":0.001285484,"domain_scores_codex":[0.9936098,0.00303203,0.0003559935,0.00103486,0.001713551,0.0002537356],"domain_scores_gemma":[0.9823639,0.01222053,0.001182221,0.001839467,0.002035884,0.0003580224],"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":[0.0006624349,0.0006528007,0.001460317,0.0003782133,0.0001547868,0.0001731811,0.0003967032,0.2409996,0.01263645,0.03353859,0.008434546,0.7005124],"study_design_scores_gemma":[0.00001992112,0.00003189369,0.00006270243,0.00001013451,0.000008890358,0.00002386525,0.00001439761,0.9806157,0.002637119,0.01592086,0.0006436359,0.00001090747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003403928,0.0003098061,0.9951007,0.0002135301,0.00005535627,0.00004736336,0.00004534307,0.0004601107,0.0003638635],"genre_scores_gemma":[0.2489978,0.0005503778,0.7438403,0.0005894415,0.0004352516,0.0007524953,0.0008188804,0.0002064484,0.003809003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008279143,"threshold_uncertainty_score":0.0437848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02444210877789751,"score_gpt":0.3137702215281998,"score_spread":0.2893281127503023,"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."}}