{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000894608,0.0001202158,0.0001182481,0.0001131502,0.0002760286,0.0008785868,0.001337061,0.00002728187,4.688527e-7],"category_scores_gemma":[0.000135751,0.0001062465,0.000009205484,0.0007909129,0.0001727675,0.003513636,0.001304555,0.0003867598,0.000001426452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003093424,"about_ca_system_score_gemma":0.00004256487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001614688,"about_ca_topic_score_gemma":0.00000338447,"domain_scores_codex":[0.9988489,0.00001713741,0.0001225666,0.0004304187,0.0002908319,0.000290103],"domain_scores_gemma":[0.9988428,0.0001833506,0.00001495903,0.0008432626,0.00001461591,0.0001010097],"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":[0.000008052615,0.00005701877,0.001284994,0.0003392472,0.00005377454,0.00006718458,0.001409307,0.01182268,0.03081673,0.1551633,0.01822453,0.7807533],"study_design_scores_gemma":[0.00006519502,0.00008232503,0.0009316095,0.0002871334,0.000009595586,0.00002394468,0.00002221946,0.8750728,0.002398155,0.002347656,0.1183404,0.0004189318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09116597,0.0007877307,0.906614,0.0003438916,0.0002629699,0.00007905855,0.000108142,0.0004068856,0.0002313356],"genre_scores_gemma":[0.9669591,0.0004821863,0.03220599,0.0001618109,0.00008656699,0.000005395996,0.00007028532,0.000006762157,0.00002195378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8757931,"threshold_uncertainty_score":0.8472233,"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."}}