{"id":"W3033643657","doi":"10.1007/978-3-030-50146-4_53","title":"Feature Extraction with TF-IDF and Game-Theoretic Shadowed Sets","year":2020,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"tf–idf; Computer science; Weighting; Zipf's law; Word (group theory); Set (abstract data type); Artificial intelligence; Feature (linguistics); Natural language processing; Information retrieval; Pattern recognition (psychology); Data mining; Machine learning; Mathematics; Statistics; Term (time); Linguistics","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":[0.001967108,0.0009490114,0.001708169,0.002496348,0.0006861214,0.001843845,0.001284145,0.001063101,0.004204645],"category_scores_gemma":[0.005628221,0.0004349051,0.001589671,0.00299331,0.000656442,0.002305441,0.001105431,0.001365633,0.002702223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009989319,"about_ca_system_score_gemma":0.0009668607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003506258,"about_ca_topic_score_gemma":0.002478466,"domain_scores_codex":[0.9987388,0.000292863,0.000108476,0.0003410372,0.0004002542,0.0001185755],"domain_scores_gemma":[0.9987016,0.0006977274,0.00006239637,0.0002003554,0.0003023872,0.00003551449],"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":[0.0002326368,0.0001012744,0.0006568782,0.0002317009,0.00009912801,0.0001249032,0.0001062037,0.04586091,0.01383912,0.0412102,0.008428489,0.8891086],"study_design_scores_gemma":[0.00002002193,0.00009040384,0.0009196153,0.0000419289,0.00004549269,0.0001982358,0.00005006378,0.9092325,0.00997129,0.0721816,0.007199991,0.00004879936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002556781,0.0003776657,0.9954396,0.00008211377,0.00008480845,0.00003686117,0.0002069125,0.0003942951,0.0008209349],"genre_scores_gemma":[0.1246783,0.0007662829,0.8667611,0.0001066709,0.0002100111,0.0001998323,0.001431217,0.0001675912,0.005678928],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004204645,"threshold_uncertainty_score":0.01406586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02166896143836028,"score_gpt":0.2582292001622964,"score_spread":0.2365602387239362,"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."}}