{"id":"W4286449976","doi":"10.18280/ria.360307","title":"A New Supervised Term Weight Measure Based Approach for Text Classification","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Term (time); Computer science; Measure (data warehouse); Task (project management); Identification (biology); Support vector machine; tf–idf; Categorization; Text categorization; Artificial intelligence; Information retrieval; Document classification; Natural language processing; Pattern recognition (psychology); Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.0005582798,0.0001986076,0.0002046765,0.0002735192,0.0005939251,0.0001986929,0.001957466,0.00008015799,0.0002941797],"category_scores_gemma":[0.0001054204,0.0002034269,0.0001717282,0.001048789,0.00005787709,0.0003347291,0.0002677122,0.0002392926,0.00007902212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535736,"about_ca_system_score_gemma":0.0001972165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008904285,"about_ca_topic_score_gemma":0.000001062772,"domain_scores_codex":[0.9979701,0.00008362723,0.0004557416,0.0007467961,0.0003617157,0.0003820354],"domain_scores_gemma":[0.9981765,0.0001705732,0.0001868572,0.001247199,0.0001140147,0.0001048526],"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":[0.00005729685,0.0004354932,0.0002965024,0.00006311876,0.00002145033,0.000002079001,0.001050606,0.01476051,0.02297463,0.3385165,0.01594804,0.6058738],"study_design_scores_gemma":[0.0001307363,0.0001813593,0.0000762051,0.000008414831,0.000009547644,0.000006758341,0.000771962,0.9015503,0.05327737,0.004489286,0.03921439,0.0002836789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004543549,0.0002697231,0.9897358,0.004753737,0.0003125656,0.0007515175,0.000009399748,0.0006240103,0.003088924],"genre_scores_gemma":[0.8362714,0.00001233198,0.1588137,0.0002617687,0.00006762872,0.0007002999,0.00005352289,0.00002171884,0.003797612],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8867898,"threshold_uncertainty_score":0.8295509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07099948823014113,"score_gpt":0.2729647282679941,"score_spread":0.201965240037853,"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."}}