{"id":"W4251596819","doi":"10.1007/978-3-540-78646-7_22","title":"Automatic Extraction of Domain-Specific Stopwords from Labeled Documents","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Classifier (UML); Information loss; Filter (signal processing); Data mining; Set (abstract data type); Artificial intelligence; Information retrieval","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005685133,0.0004611121,0.0007144873,0.0009218386,0.00022429,0.0003105444,0.00324057,0.0002685499,0.00009807832],"category_scores_gemma":[0.00002816236,0.0004235386,0.0001835756,0.0008394179,0.0005470251,0.0008323549,0.0008830786,0.0005886424,0.00007184635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000241596,"about_ca_system_score_gemma":0.0003357242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009649203,"about_ca_topic_score_gemma":0.00003643994,"domain_scores_codex":[0.9960269,0.00005559881,0.0007367163,0.001409783,0.001294151,0.0004768731],"domain_scores_gemma":[0.9966972,0.0005081561,0.0005803902,0.001882266,0.0001896217,0.0001423012],"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":[0.000005330824,0.00008038662,0.000136131,0.00002757705,0.00006076199,0.0001644221,0.001761362,0.00359744,0.001781219,0.003539741,0.000313313,0.9885323],"study_design_scores_gemma":[0.001720727,0.000497993,0.002765621,0.002203528,0.00007830363,0.000229893,0.000002212671,0.7865798,0.008852035,0.1558921,0.03845384,0.002723909],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005549271,0.0008302531,0.9907745,0.0002089819,0.00116562,0.0001661493,0.00002022944,0.0001387368,0.001146309],"genre_scores_gemma":[0.1770677,0.0003736501,0.821592,0.0002720333,0.0003798171,0.000005874115,0.00003567184,0.00003178826,0.0002414825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9858084,"threshold_uncertainty_score":0.9998217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01686015710638942,"score_gpt":0.2507353239094569,"score_spread":0.2338751668030674,"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."}}