{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001465413,0.00006142944,0.0001113659,0.001045441,0.0002919645,0.000429807,0.0001420467,0.00003486913,0.00006961425],"category_scores_gemma":[0.0002837087,0.00004675167,0.00003523999,0.008901986,0.0001891716,0.0001788805,0.00004576739,0.0000870036,0.00001897524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006472406,"about_ca_system_score_gemma":0.0001574855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002205422,"about_ca_topic_score_gemma":0.0003273469,"domain_scores_codex":[0.9986354,0.00006568899,0.0001134139,0.0002410912,0.0007492788,0.0001951477],"domain_scores_gemma":[0.9992712,0.0003704178,0.00002368538,0.00007687161,0.0001231825,0.0001346823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000585526,0.00006416789,0.0393551,0.00003697065,0.00004876043,0.00001126444,0.01562536,0.003058039,0.00002324151,0.418642,0.002887092,0.5202422],"study_design_scores_gemma":[0.0002205598,0.00009559433,0.02207676,0.00004342265,0.00009523424,0.000002982934,0.00220247,0.4350793,0.00006114396,0.03086521,0.5088897,0.0003676525],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4774364,0.00519275,0.3526189,0.004740103,0.001016506,0.0002329908,0.000007815504,0.0002976059,0.158457],"genre_scores_gemma":[0.9727854,0.00005375898,0.01926677,0.00008880592,0.0001158114,0.000002659086,0.000002042796,0.000004370612,0.007680406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5198746,"threshold_uncertainty_score":0.4277109,"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."}}