{"id":"W2470734381","doi":"10.29173/cais279","title":"Automatic Classification and Categorization: Application for Identifying and Thematic Analysing of Textual Unstructured Documents","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Thematic map; Categorization; Computer science; Focus (optics); Suite; Humanities; Information retrieval; Library science; Artificial intelligence; Cartography; Geography; Art; Physics","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":[0.004198889,0.0008629416,0.0009570262,0.009437226,0.002177435,0.003149149,0.001825358,0.001968584,0.005326558],"category_scores_gemma":[0.01011597,0.0004329456,0.001223681,0.00708377,0.00104679,0.002851376,0.001450418,0.001109525,0.00375237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001276829,"about_ca_system_score_gemma":0.00226428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00510323,"about_ca_topic_score_gemma":0.005023654,"domain_scores_codex":[0.9967011,0.001043239,0.0002984159,0.0006520567,0.001044634,0.0002605656],"domain_scores_gemma":[0.9932421,0.003432279,0.0005391314,0.0008508464,0.001708976,0.0002267771],"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":[0.0002218641,0.000276986,0.005795278,0.0007481313,0.00008463491,0.0002956083,0.003360541,0.00269909,0.0332158,0.01135103,0.01375935,0.9281917],"study_design_scores_gemma":[0.000239946,0.0004804226,0.04753441,0.0009835601,0.000300443,0.003220891,0.01494934,0.4796593,0.1048212,0.1200716,0.2273211,0.0004177381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03595212,0.0009897772,0.9411653,0.001122035,0.0003443391,0.001634768,0.001602733,0.007411756,0.009777277],"genre_scores_gemma":[0.07677349,0.0003230248,0.9149567,0.0001413056,0.00009109262,0.0009426717,0.001388277,0.0002593966,0.005124029],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009437226,"threshold_uncertainty_score":0.02220613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03325449017504562,"score_gpt":0.2870277427042244,"score_spread":0.2537732525291788,"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."}}