{"id":"W4400967584","doi":"","title":"Analyse non supervisée de corpus de documents pour la recherche de sujets : une nouvelle approche basée sur le clustering et la maximisation des traits","year":2024,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; Université du Québec à Montréal","keywords":"Computer science; Cluster analysis; Humanities; Artificial intelligence; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01717077,0.0003606989,0.0003040083,0.0002248752,0.000573082,0.002012688,0.001609472,0.0004106934,0.00005296832],"category_scores_gemma":[0.001741953,0.0004176564,0.0001915847,0.001626823,0.0003331569,0.001024503,0.0007587447,0.0008763489,0.00007180772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005633262,"about_ca_system_score_gemma":0.00181965,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01314236,"about_ca_topic_score_gemma":0.006623974,"domain_scores_codex":[0.9884083,0.009060407,0.0005403643,0.0008993208,0.000367767,0.0007237855],"domain_scores_gemma":[0.9925901,0.004787741,0.0002010098,0.001221922,0.0008236971,0.0003755439],"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":[0.000009094104,0.0009491245,0.0007813049,0.0003685693,0.0001283619,0.00004172068,0.09352762,0.0006556243,0.02447928,0.05299894,0.002343262,0.8237171],"study_design_scores_gemma":[0.0006211854,0.000001913334,0.007190853,0.001965945,0.00009013682,0.0002298317,0.0009861268,0.8940173,0.02712979,0.007860787,0.05943163,0.0004744792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09568321,0.001776378,0.8576155,0.02457561,0.0001074507,0.000275203,0.00008911987,0.0002832256,0.01959435],"genre_scores_gemma":[0.336906,0.001638796,0.6366792,0.0001958834,0.00003904206,0.0001069681,0.0001734267,0.00006345804,0.0241973],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8933617,"threshold_uncertainty_score":0.9998275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1371768219059175,"score_gpt":0.3074384311851966,"score_spread":0.1702616092792791,"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."}}