{"id":"W4412819086","doi":"10.18280/ria.390301","title":"Ontology-Driven Text Classification and Data Mining: Beyond Keywords Toward Semantic Intelligence","year":2025,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Ontology; Information retrieval; Text mining; Natural language processing; Artificial intelligence; Data science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005782001,0.0007279155,0.001162591,0.00905354,0.000951077,0.005712618,0.001668187,0.001135633,0.00122305],"category_scores_gemma":[0.0172191,0.0002967378,0.001628665,0.01042895,0.001933282,0.01534812,0.002658915,0.002202108,0.001325897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001955529,"about_ca_system_score_gemma":0.003640678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003181136,"about_ca_topic_score_gemma":0.003717734,"domain_scores_codex":[0.9943088,0.001922813,0.0006551843,0.0008372238,0.002062482,0.0002135418],"domain_scores_gemma":[0.9914618,0.004884906,0.0007965527,0.001047443,0.001575572,0.0002336636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001020065,0.000168809,0.006661805,0.001561512,0.0001786987,0.00017146,0.001593034,0.007884686,0.005766623,0.1431944,0.01157597,0.8211411],"study_design_scores_gemma":[0.00002686325,0.00008962079,0.003787157,0.001505115,0.0001659415,0.000484076,0.002780766,0.1854451,0.01656074,0.6428746,0.1461672,0.0001127508],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01601428,0.008074114,0.959776,0.006518057,0.0003136937,0.0003154715,0.001470743,0.001705262,0.005812304],"genre_scores_gemma":[0.1927475,0.01071639,0.7855005,0.001479642,0.0004548605,0.000389622,0.005021131,0.0004020893,0.003288306],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00905354,"threshold_uncertainty_score":0.03057849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.103687463890506,"score_gpt":0.3350575150056456,"score_spread":0.2313700511151396,"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."}}