{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006957265,0.0002772684,0.0003880964,0.0002900964,0.0002750797,0.0003129164,0.003009165,0.0001837107,0.00003753869],"category_scores_gemma":[0.0005944118,0.0002674631,0.00006383527,0.0009448988,0.0003621163,0.0006200719,0.001412191,0.0002602651,0.0001799047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005175822,"about_ca_system_score_gemma":0.0001492634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007874717,"about_ca_topic_score_gemma":0.0001344623,"domain_scores_codex":[0.9972346,0.0001190756,0.000691637,0.001236622,0.0002091512,0.0005089541],"domain_scores_gemma":[0.9965714,0.0006336899,0.000186651,0.002343479,0.0001543392,0.000110415],"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":[0.00002205053,0.0002168019,0.009964086,0.000214336,0.00008284545,0.00004243754,0.004223795,0.001020743,0.001610798,0.347356,0.003963769,0.6312823],"study_design_scores_gemma":[0.00003885602,0.0000838501,0.002743554,0.0001619017,0.00004003667,0.00004878268,0.002734732,0.9606088,0.007046942,0.01879265,0.007366149,0.0003337281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01597506,0.002113516,0.9605602,0.01021749,0.00101024,0.0003308658,0.000006000695,0.0002653288,0.009521316],"genre_scores_gemma":[0.9593757,0.0006321297,0.0377831,0.0005248684,0.00005725277,0.00002283799,0.00001704051,0.00001113919,0.00157587],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9595881,"threshold_uncertainty_score":0.9999778,"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."}}