{"id":"W3108900336","doi":"10.1007/978-3-030-63119-2_65","title":"Textual Clustering: Towards a More Efficient Descriptors of Texts","year":2020,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Cluster analysis; Hierarchical clustering; Computer science; Medoid; Artificial intelligence; Data mining; Artificial neural network; Document clustering; Pattern recognition (psychology); Brown clustering; Information retrieval; Correlation clustering; Canopy clustering algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005774585,0.0002062857,0.0002780429,0.0006274104,0.0002872031,0.0004082652,0.004271391,0.00009204962,0.000004210089],"category_scores_gemma":[0.00004935739,0.0002041158,0.00005111739,0.0006016084,0.0009492383,0.002472754,0.004217134,0.0003282484,0.00003328926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008976136,"about_ca_system_score_gemma":0.0003729565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000190049,"about_ca_topic_score_gemma":0.000003100229,"domain_scores_codex":[0.9982426,0.00001564315,0.0007379434,0.000319895,0.0004950445,0.0001889289],"domain_scores_gemma":[0.9969587,0.00008959917,0.0003853607,0.002066454,0.0003624293,0.0001374246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001038485,0.00001921818,0.000004703354,0.00002941222,0.000004596202,2.299657e-7,0.002082814,0.0004830579,0.000005443648,0.533292,0.0002811438,0.4637964],"study_design_scores_gemma":[0.0001679458,0.00004869925,0.0005037547,0.0001479911,0.000004807181,0.00001370056,0.00005465217,0.9200708,0.00001928193,0.0008452828,0.07790112,0.0002220008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003420446,0.0002043071,0.8687453,0.002021539,0.000131633,0.0003512915,0.00006475504,0.0000914664,0.1283555],"genre_scores_gemma":[0.1035067,0.0009451652,0.893097,0.001561961,0.00005673586,0.00005813618,0.0001450418,0.00001749315,0.0006118036],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9195877,"threshold_uncertainty_score":0.8323599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04596565457403039,"score_gpt":0.2916378477862309,"score_spread":0.2456721932122005,"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."}}