{"id":"W4385144683","doi":"10.1186/s12911-023-02216-1","title":"Quality indices for topic model selection and evaluation: a literature review and case study","year":2023,"lang":"en","type":"review","venue":"BMC Medical Informatics and Decision Making","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Topic model; Artificial intelligence; Automatic summarization; Natural language processing; Model selection; Statistic; Information retrieval; Cluster analysis; Machine learning; Data mining; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0951167,0.002301533,0.005015519,0.01594582,0.001369936,0.006886744,0.004215716,0.003251581,0.001997431],"category_scores_gemma":[0.2503993,0.00127624,0.005106919,0.01613364,0.00210898,0.00620774,0.002394635,0.003798282,0.0006890998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005008863,"about_ca_system_score_gemma":0.005350334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006643047,"about_ca_topic_score_gemma":0.005525142,"domain_scores_codex":[0.9435896,0.03275739,0.009592783,0.003542337,0.01001282,0.0005050572],"domain_scores_gemma":[0.5754099,0.3819139,0.01153001,0.004412035,0.02576527,0.0009688055],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0003779675,0.000215165,0.01290586,0.02954539,0.001410036,0.0001383418,0.001224705,0.007931665,0.0003656553,0.009082538,0.0124453,0.9243575],"study_design_scores_gemma":[0.0008240308,0.003533151,0.06311484,0.2493329,0.01673631,0.005799481,0.008208917,0.2857907,0.009028933,0.08919491,0.2666184,0.00181746],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.006981282,0.9278173,0.05732977,0.003752464,0.0003195849,0.0006099647,0.0004322297,0.0002964765,0.002460867],"genre_scores_gemma":[0.1726412,0.6455066,0.1723532,0.002179694,0.001533594,0.00251277,0.002198032,0.0004496524,0.0006252851],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9048833,"threshold_uncertainty_score":0.5030312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2952128063180214,"score_gpt":0.5148011429221888,"score_spread":0.2195883366041674,"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."}}