{"id":"W3035362865","doi":"10.1142/s2196888820500207","title":"New Descriptors of Textual Records: Getting Help from Frequent Itemsets","year":2020,"lang":"en","type":"article","venue":"Vietnam Journal of Computer Science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Data mining; Medoid; Keyword extraction; Information retrieval; Set (abstract data type); Similarity (geometry); Process (computing); Raw data; Document clustering; Association rule learning; Artificial intelligence","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":[0.001296225,0.0008500905,0.001156106,0.01166291,0.0005408824,0.001859528,0.001277076,0.001153495,0.003659215],"category_scores_gemma":[0.01234232,0.0003437664,0.0007815165,0.01009877,0.0003622206,0.00302328,0.001147326,0.0008160181,0.003408673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004682995,"about_ca_system_score_gemma":0.0007718226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001446822,"about_ca_topic_score_gemma":0.001652489,"domain_scores_codex":[0.9983699,0.0002463986,0.0003433583,0.0003639228,0.0005663914,0.0001100188],"domain_scores_gemma":[0.9934765,0.003454051,0.0007542495,0.000713576,0.001388365,0.0002132438],"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":[0.0008411327,0.0004554029,0.02489039,0.001676497,0.000155503,0.001598357,0.0009211871,0.005413111,0.01981913,0.007841696,0.01896275,0.9174249],"study_design_scores_gemma":[0.0004725104,0.001741975,0.06703277,0.001232191,0.0007065159,0.00950805,0.007892387,0.608746,0.06376705,0.08594128,0.1524787,0.0004806684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1554822,0.004332075,0.7784571,0.001452046,0.0006771622,0.001503885,0.04182137,0.009705597,0.00656852],"genre_scores_gemma":[0.2912031,0.002029809,0.6644365,0.0002183237,0.0004223435,0.0008895684,0.03726076,0.00031252,0.003227112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01166291,"threshold_uncertainty_score":0.0122413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0265998240732124,"score_gpt":0.2530871985306625,"score_spread":0.2264873744574501,"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."}}