{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008535432,0.001148373,0.001376529,0.005669018,0.0008802644,0.002304903,0.002451598,0.001114164,0.009847592],"category_scores_gemma":[0.003915785,0.0004572754,0.001228954,0.008366591,0.0006324499,0.00298691,0.001697994,0.001201704,0.009248912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009248882,"about_ca_system_score_gemma":0.001411337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003466799,"about_ca_topic_score_gemma":0.004124969,"domain_scores_codex":[0.9987127,0.000190259,0.0001285128,0.0003776025,0.0005061327,0.0000848714],"domain_scores_gemma":[0.998028,0.0004525061,0.000168836,0.0005459937,0.0006898848,0.0001147779],"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":[0.0002960069,0.0001422369,0.001173138,0.000644993,0.00009795332,0.00007229515,0.000247234,0.008277894,0.04129627,0.02387893,0.04185697,0.8820161],"study_design_scores_gemma":[0.000113946,0.0003763456,0.007583918,0.0002972288,0.0003224008,0.001217706,0.0006488106,0.5936561,0.09253158,0.09710136,0.2059696,0.0001810629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01097205,0.001650737,0.9732107,0.0003729127,0.0002923303,0.0001981117,0.004857679,0.004899957,0.00354555],"genre_scores_gemma":[0.04840528,0.001532036,0.9137632,0.0002368865,0.0004244102,0.0003841133,0.01476868,0.001152681,0.01933266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009847592,"threshold_uncertainty_score":0.03294343,"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."}}