{"id":"W2971324562","doi":"10.1007/978-3-030-28374-2_4","title":"Frequent Itemsets as Descriptors of Textual Records","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Medoid; Similarity (geometry); Data mining; Set (abstract data type); Hierarchical clustering; Process (computing); Association rule learning; Cluster analysis; Artificial intelligence; Information retrieval; Data set; Pattern recognition (psychology); Natural language processing","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":[0.000642983,0.0004941956,0.000651528,0.008209794,0.0004447495,0.001947276,0.0009292512,0.0006078847,0.00230853],"category_scores_gemma":[0.005116454,0.0003637175,0.0006503933,0.008960442,0.0003963454,0.002771086,0.0006526358,0.0006239123,0.001212073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005822981,"about_ca_system_score_gemma":0.0004934458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008109273,"about_ca_topic_score_gemma":0.001012171,"domain_scores_codex":[0.9989145,0.000187054,0.0001978222,0.0002171179,0.0004110041,0.00007258439],"domain_scores_gemma":[0.99747,0.001536161,0.0003716105,0.0001887994,0.0003400454,0.00009335709],"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":[0.001964812,0.0005906916,0.02765022,0.002374619,0.0003765371,0.003127952,0.001486194,0.02060756,0.04057754,0.1129767,0.02842089,0.7598463],"study_design_scores_gemma":[0.0003089925,0.001435429,0.0465914,0.0008945378,0.0006470948,0.008122156,0.002999587,0.4954373,0.03239477,0.3074138,0.1034923,0.0002626325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4070784,0.01590963,0.5231001,0.001178521,0.001026924,0.0008585145,0.03706073,0.003933761,0.009853343],"genre_scores_gemma":[0.6791566,0.004623665,0.2639203,0.0001670691,0.0006465368,0.0006479555,0.04213863,0.0001758617,0.008523317],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008209794,"threshold_uncertainty_score":0.007722735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01979408017618044,"score_gpt":0.2542030724421918,"score_spread":0.2344089922660114,"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."}}