{"id":"W4386004792","doi":"10.1007/978-3-031-33261-6_8","title":"Topic Modelling for Automatically Identification of Relevant Concepts Discussed in Academic Documents","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Identification (biology); Visualization; Coherence (philosophical gambling strategy); Data science; Information retrieval; Natural language processing; 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":[0.002449191,0.001442643,0.001158474,0.007861168,0.001183715,0.002793995,0.001285965,0.001765346,0.004618056],"category_scores_gemma":[0.007787387,0.0005635273,0.002192213,0.005798424,0.0004695632,0.00335335,0.001888015,0.002009535,0.005081669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111091,"about_ca_system_score_gemma":0.00166989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005109023,"about_ca_topic_score_gemma":0.005712027,"domain_scores_codex":[0.9977171,0.0007502048,0.0002409671,0.0005661984,0.0005039726,0.0002215997],"domain_scores_gemma":[0.9952179,0.003329682,0.0002842849,0.0002577767,0.0007179354,0.0001924515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001305341,0.0004920601,0.007708318,0.002052212,0.0003945903,0.0005154067,0.001929013,0.01214245,0.04460681,0.01057592,0.06577677,0.8525011],"study_design_scores_gemma":[0.0002151389,0.0004081824,0.01471589,0.0004554116,0.0008510367,0.001565492,0.001675718,0.8276526,0.03913978,0.03440118,0.07873441,0.0001852193],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07111449,0.01136961,0.8802661,0.001145725,0.0007110201,0.000786229,0.01064433,0.01674338,0.007219179],"genre_scores_gemma":[0.4104803,0.004694478,0.5406559,0.0003775343,0.0008724336,0.001388444,0.03073517,0.001385836,0.009409954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007861168,"threshold_uncertainty_score":0.01544893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03895559091644764,"score_gpt":0.2946035290801671,"score_spread":0.2556479381637195,"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."}}