{"id":"W1902658720","doi":"10.5430/air.v4n2p143","title":"A text feature selection method based on category-distribution divergence","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Feature selection; Selection (genetic algorithm); Divergence (linguistics); Artificial intelligence; Computer science; Feature (linguistics); Natural language processing; Pattern recognition (psychology); Distribution (mathematics); Mathematics; Statistics; Linguistics; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003100363,0.0001496505,0.00013753,0.0003793136,0.0004085545,0.0004190191,0.001321091,0.000184214,0.00005229378],"category_scores_gemma":[0.00147859,0.0001334884,0.00005974423,0.002807249,0.0001864153,0.0004624847,0.0002602459,0.0006456966,0.001205782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003777277,"about_ca_system_score_gemma":0.0003831736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001960294,"about_ca_topic_score_gemma":0.00004637824,"domain_scores_codex":[0.9969063,0.0004635027,0.0002581129,0.000637859,0.001153569,0.0005806629],"domain_scores_gemma":[0.9977787,0.0004178565,0.00007295575,0.0006789595,0.0008571496,0.0001943973],"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":[0.0000496039,0.0001696114,0.0002047632,0.00000546519,0.000004659455,0.000005961976,0.0002199546,0.002704973,0.002227261,0.5810205,0.01370367,0.3996836],"study_design_scores_gemma":[0.000028416,0.0004085347,0.0001603213,0.00001275087,0.000001736491,0.000003022417,0.0005358858,0.5914442,0.2316163,0.1631665,0.01245508,0.0001671979],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001673783,0.00005077785,0.9833659,0.01219864,0.0002694495,0.0003253588,0.000004597644,0.0004719461,0.001639538],"genre_scores_gemma":[0.9748663,0.00001518519,0.02426932,0.00008245995,0.00007798951,0.00009670544,0.00001617862,0.000008733034,0.0005671544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9731925,"threshold_uncertainty_score":0.9995719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2404044412835338,"score_gpt":0.445637965919208,"score_spread":0.2052335246356742,"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."}}