{"id":"W4396237870","doi":"10.1007/s11192-024-05017-z","title":"CFMf topic-model: comparison with LDA and Top2Vec","year":2024,"lang":"en","type":"article","venue":"Scientometrics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"Social Sciences and Humanities Research Council of Canada; Fonds de Recherche du Québec-Société et Culture; Canada Research Chairs","keywords":"Computer science; Topic model; Data science; Information retrieval","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.005662751,0.001582748,0.00145171,0.00574784,0.001265388,0.002206641,0.001178671,0.001454785,0.006297775],"category_scores_gemma":[0.01383139,0.000273549,0.001375929,0.004317834,0.0003373071,0.003851136,0.001096023,0.001311442,0.00425196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009614684,"about_ca_system_score_gemma":0.002755435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02530421,"about_ca_topic_score_gemma":0.02602948,"domain_scores_codex":[0.9974137,0.001322012,0.0001485452,0.0004364312,0.0004907686,0.0001885505],"domain_scores_gemma":[0.9932869,0.003920843,0.0001702316,0.000853373,0.001524483,0.0002440468],"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":[0.003293368,0.001077819,0.01656394,0.0012114,0.001305019,0.0001049486,0.0003344045,0.06694724,0.003636194,0.005107389,0.07525824,0.8251601],"study_design_scores_gemma":[0.0002298013,0.0005426885,0.008341214,0.0001164238,0.0004913189,0.0002687766,0.000277905,0.9653425,0.003012289,0.006543935,0.0147267,0.0001064781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3411925,0.02316828,0.5492099,0.003117439,0.003239533,0.001000611,0.02590372,0.03093638,0.02223179],"genre_scores_gemma":[0.7202412,0.005415181,0.2146517,0.0004380302,0.001172316,0.000680568,0.04490734,0.002122884,0.01037065],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9942521,"threshold_uncertainty_score":0.05031383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08423497244561039,"score_gpt":0.4562715976662367,"score_spread":0.3720366252206262,"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."}}