{"id":"W2784269545","doi":"10.1007/s10115-017-1147-9","title":"Localized user-driven topic discovery via boosted ensemble of nonnegative matrix factorization","year":2018,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Research Foundation of Korea","keywords":"Matrix decomposition; Computer science; Factorization; Matrix (chemical analysis); Non-negative matrix factorization; Mathematics; Artificial intelligence; Algorithm; Physics","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":[0.0001543487,0.0001146263,0.0002326449,0.0002290029,0.00009510397,0.0001563189,0.0002500832,0.00007590473,0.000002684196],"category_scores_gemma":[0.00003804567,0.00009677953,0.00004132434,0.0004858999,0.00005774459,0.006133218,0.0001267785,0.00004915813,0.00005639518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005083238,"about_ca_system_score_gemma":0.00003819415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000356293,"about_ca_topic_score_gemma":0.00001170187,"domain_scores_codex":[0.9990214,0.0000616472,0.0004989724,0.0001235512,0.0001675987,0.0001268333],"domain_scores_gemma":[0.9987667,0.00005285812,0.0003368756,0.000302989,0.0004961364,0.00004443526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007458949,0.0001865604,0.009965869,0.001120831,0.000285773,0.000001397207,0.04960113,0.0003686531,0.02266013,0.7827153,0.004224543,0.1287952],"study_design_scores_gemma":[0.001671128,0.0006605422,0.00333431,0.000424275,0.00005095641,0.00002177857,0.0008624777,0.6680446,0.1221101,0.002384871,0.1996928,0.0007421745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008855678,0.0001222469,0.9843863,0.00001574141,0.0002505577,0.0002661603,0.000004046501,0.0001296512,0.005969643],"genre_scores_gemma":[0.994166,0.00002827914,0.00522039,0.00001802115,0.00007275007,0.00001907101,0.00001823103,0.000003839366,0.0004534586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9853103,"threshold_uncertainty_score":0.4446435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009477174681492609,"score_gpt":0.2722200081363226,"score_spread":0.26274283345483,"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."}}