{"id":"W4393347796","doi":"10.1007/s41019-023-00239-2","title":"Uncovering Flat and Hierarchical Topics by Community Discovery on Word Co-occurrence Network","year":2024,"lang":"en","type":"article","venue":"Data Science and Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; University of Alberta","funders":"Centre National de la Recherche Scientifique; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Hierarchy; Identification (biology); Topic model; Word (group theory); Exploit; Data science; Tree (set theory); Information retrieval; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001791662,0.001398175,0.001220016,0.01111595,0.001523715,0.001608342,0.001333717,0.001299595,0.0008332788],"category_scores_gemma":[0.006843528,0.000492062,0.001454037,0.006835887,0.0008192831,0.003979882,0.002131102,0.001231576,0.000763652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007747484,"about_ca_system_score_gemma":0.001228158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006110988,"about_ca_topic_score_gemma":0.008862048,"domain_scores_codex":[0.9981628,0.0004970985,0.00010017,0.0006103496,0.0004274637,0.0002021678],"domain_scores_gemma":[0.9953041,0.002745843,0.0006722467,0.0003606623,0.0006919269,0.0002251383],"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":[0.001003416,0.0005659446,0.05207582,0.00116259,0.0006551389,0.001232364,0.003487588,0.1104807,0.02586428,0.02857766,0.01928394,0.7556105],"study_design_scores_gemma":[0.00004122082,0.00006823376,0.005045797,0.00007539419,0.0001326399,0.0004430249,0.0006327314,0.9463732,0.005070652,0.03491358,0.007153866,0.00004963932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1057074,0.002552721,0.8852381,0.0004530801,0.00007654077,0.0003280116,0.001625949,0.001611414,0.002406876],"genre_scores_gemma":[0.5231264,0.001450459,0.4648589,0.0001254601,0.0002459289,0.0004391874,0.006579452,0.0002795194,0.002894678],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01111595,"threshold_uncertainty_score":0.01215082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02326652083480183,"score_gpt":0.2920903359651108,"score_spread":0.268823815130309,"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."}}