{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005023917,0.0002183629,0.000256772,0.0004891603,0.0004246176,0.000957376,0.001605805,0.0001051109,0.000006711105],"category_scores_gemma":[0.00002525347,0.0001867475,0.00003396839,0.0004876818,0.0008164466,0.005619821,0.001492163,0.0004778495,0.0000193044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006208602,"about_ca_system_score_gemma":0.0001392488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005676987,"about_ca_topic_score_gemma":0.00000973357,"domain_scores_codex":[0.9987373,0.00002377521,0.0003597615,0.0003224198,0.0003741477,0.0001825599],"domain_scores_gemma":[0.9979151,0.0001210811,0.0003506242,0.001225654,0.0002571031,0.0001303759],"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":[0.000004896995,0.000006235487,0.00003979529,0.00003284511,0.000009811482,0.000001108374,0.001941573,0.0001816032,0.000003052394,0.7201875,0.0001725171,0.277419],"study_design_scores_gemma":[0.0002592958,0.0001211035,0.001249482,0.000220828,0.00001667467,0.0001088738,0.0000503554,0.870604,0.000005543344,0.006811945,0.1201925,0.0003594126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001969605,0.0009880163,0.764078,0.009435642,0.0001839804,0.0005477214,0.00001608256,0.0001942505,0.2243593],"genre_scores_gemma":[0.3984552,0.006087066,0.5894198,0.003199574,0.00009298675,0.00003983437,0.0001436017,0.00003227953,0.002529592],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8704224,"threshold_uncertainty_score":0.9231999,"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."}}