{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007282466,0.0002175897,0.0005149763,0.0001755089,0.00003467444,0.00008270498,0.0004282612,0.0005379097,6.035526e-7],"category_scores_gemma":[0.00005616956,0.000183887,0.00006622356,0.00008622347,0.00003228892,0.000110189,0.0001109067,0.000459568,0.000001008102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006955978,"about_ca_system_score_gemma":0.00003706126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004321327,"about_ca_topic_score_gemma":0.00003320971,"domain_scores_codex":[0.9979348,0.00004422916,0.001011436,0.0005081619,0.0002447132,0.0002566572],"domain_scores_gemma":[0.9985783,0.0005503896,0.0003653449,0.0004099211,0.00005439787,0.00004166977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004274405,0.000002695384,0.00007017626,0.000281612,0.0000137484,0.000003215052,0.0004504957,0.8932043,0.00001989532,0.09359074,0.000006249396,0.01235263],"study_design_scores_gemma":[0.0002387238,0.0000177674,0.00001834101,0.001125449,0.000008932243,0.000002167406,0.000002739012,0.921887,0.00000544872,0.07638414,0.0001454703,0.0001637495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003740351,0.002300948,0.9949937,0.0001668089,0.0009906256,0.000832407,0.000004643418,0.00005540689,0.0002813996],"genre_scores_gemma":[0.9911765,0.0006116481,0.003697341,0.00003862338,0.0003260552,0.00008566067,0.00002174356,0.00003858417,0.004003797],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9912964,"threshold_uncertainty_score":0.7498693,"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."}}