{"id":"W7126175451","doi":"10.18280/isi.301208","title":"A Comparative Evaluation of LDA, NMF, and BERTopic: Analyzing Perplexity and Coherence Metrics","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Perplexity; Coherence (philosophical gambling strategy); Pattern recognition (psychology); Key (lock)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01072371,0.001833972,0.00103369,0.006982508,0.0009319027,0.001719441,0.001087469,0.001230803,0.001220905],"category_scores_gemma":[0.02927459,0.0003156282,0.001049367,0.00328463,0.00107594,0.003186551,0.002291878,0.001177572,0.0006334649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001492375,"about_ca_system_score_gemma":0.001187628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005801311,"about_ca_topic_score_gemma":0.008563203,"domain_scores_codex":[0.9945121,0.003169539,0.0003372477,0.0009721594,0.0007925047,0.0002163279],"domain_scores_gemma":[0.9771846,0.01796531,0.0006405532,0.002050724,0.00165817,0.000500541],"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":[0.003099595,0.0008354636,0.07572566,0.001538791,0.001337616,0.0003306585,0.001820253,0.1666262,0.01792126,0.007878309,0.01616401,0.7067222],"study_design_scores_gemma":[0.0001281192,0.0007294127,0.02861369,0.0001035271,0.0001555915,0.000361532,0.0008467535,0.9425787,0.01240912,0.01035933,0.003585814,0.0001284941],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7136372,0.005309262,0.2589158,0.0009908503,0.0002371481,0.0004341351,0.004397756,0.009107932,0.006969946],"genre_scores_gemma":[0.8614906,0.0008508613,0.1262996,0.0001312858,0.0001099306,0.0003327627,0.008831215,0.0006394704,0.001314341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01072371,"threshold_uncertainty_score":0.0567131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02111578434179858,"score_gpt":0.2924146304819231,"score_spread":0.2712988461401245,"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."}}