{"id":"W4410546712","doi":"10.18280/isi.300408","title":"An Accurate Model for Text Document Classification Using Machine Learning Techniques","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Document classification; Natural language processing; Information retrieval","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":[0.00052623,0.0001762103,0.0001669817,0.0005220123,0.0005160309,0.0008280893,0.0007225668,0.0001455098,0.000003064331],"category_scores_gemma":[0.0001852983,0.0001698084,0.00005980046,0.0005790431,0.00008107002,0.007213258,0.0001275212,0.0001381731,0.000009058124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003736271,"about_ca_system_score_gemma":0.0001393616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002946723,"about_ca_topic_score_gemma":0.000005092054,"domain_scores_codex":[0.9987155,0.000045382,0.0005788843,0.0002211788,0.0001803058,0.0002587217],"domain_scores_gemma":[0.9986945,0.0000557593,0.0003871276,0.0005108027,0.0003112565,0.00004053783],"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":[0.00002471916,0.00003494558,0.000569278,0.0001762378,0.00002289875,1.144211e-7,0.002289186,0.006602068,0.009157762,0.4987179,0.0001645151,0.4822403],"study_design_scores_gemma":[0.0001819567,0.00005828146,0.000311343,0.00005804616,0.000009197482,0.000001923347,0.0003602843,0.9241878,0.02062471,0.05079708,0.00323671,0.0001726981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01108942,0.00005903912,0.9850415,0.0003528509,0.0001171453,0.0006037768,0.000006209246,0.001425487,0.001304543],"genre_scores_gemma":[0.7931931,0.00003421165,0.2061464,0.0001575284,0.00001055409,0.0002223486,0.00006942503,0.000005994986,0.0001603883],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9175857,"threshold_uncertainty_score":0.7985284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03506586237580583,"score_gpt":0.304176570138292,"score_spread":0.2691107077624861,"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."}}