{"id":"W2586740849","doi":"10.29173/cais214","title":"Application of Predictive and Descriptive Text Mining Techniques for Analysis and Organization of Unstructured Documents","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Presentation (obstetrics); Humanities; Descriptive statistics; Computer science; Artificial intelligence; Philosophy; Mathematics; Statistics","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":[0.004652607,0.0008061531,0.0006368758,0.007510609,0.0009601877,0.002583966,0.001491453,0.0005866888,0.001599938],"category_scores_gemma":[0.01868218,0.0004035945,0.0009150678,0.006718438,0.0009546521,0.002882229,0.0009607098,0.001155211,0.0009546893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007506397,"about_ca_system_score_gemma":0.001855712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001690602,"about_ca_topic_score_gemma":0.002839183,"domain_scores_codex":[0.9967565,0.001066704,0.0003711035,0.0006096999,0.001099919,0.00009607621],"domain_scores_gemma":[0.977056,0.01533615,0.001946612,0.002208606,0.003137955,0.0003147346],"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":[0.0004067571,0.0004141694,0.01545104,0.001751201,0.0001705418,0.0007310994,0.006073818,0.01275392,0.03603413,0.02643047,0.005555913,0.8942268],"study_design_scores_gemma":[0.0002070579,0.00102605,0.03698108,0.001324546,0.0007231968,0.00510834,0.01253747,0.5565146,0.1249154,0.159339,0.1009826,0.0003405942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03220111,0.0005777317,0.9594219,0.0006630183,0.00006127821,0.0006892743,0.001784705,0.002123012,0.002478],"genre_scores_gemma":[0.124693,0.0004992102,0.8705398,0.00009003485,0.00006897972,0.0004855089,0.002269134,0.0001171607,0.001237118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007510609,"threshold_uncertainty_score":0.02460563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01270750199338373,"score_gpt":0.2496192151319699,"score_spread":0.2369117131385862,"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."}}