{"id":"W3043222912","doi":"10.3389/frai.2020.00042","title":"Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis","year":2020,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Latent semantic analysis; Popularity; Information retrieval; Social media; Matrix decomposition; Context (archaeology); Artificial intelligence; Precision and recall; Natural language processing; Data science; Machine learning; Data mining; World Wide Web","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02162341,0.001628618,0.001670609,0.01362742,0.0008241962,0.003625943,0.001420676,0.001817168,0.001288501],"category_scores_gemma":[0.05717194,0.0004620613,0.002518149,0.01202565,0.0007248482,0.007651937,0.001170807,0.001568822,0.001011166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001083974,"about_ca_system_score_gemma":0.001122753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002795435,"about_ca_topic_score_gemma":0.00255467,"domain_scores_codex":[0.9852224,0.008075548,0.001204108,0.001945828,0.003314315,0.0002377672],"domain_scores_gemma":[0.8810503,0.1052997,0.002955456,0.003512815,0.006563126,0.0006186923],"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":[0.001088889,0.0004043071,0.04807114,0.005398154,0.002497919,0.0003130276,0.002553266,0.03573433,0.003815238,0.01169664,0.0121784,0.8762488],"study_design_scores_gemma":[0.0001890472,0.001084155,0.09188557,0.001883877,0.001972463,0.001714524,0.004385911,0.7781143,0.008227656,0.03391255,0.07618051,0.000449441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1432417,0.1404304,0.6987153,0.0029354,0.001111174,0.000753464,0.004320539,0.002074994,0.006416977],"genre_scores_gemma":[0.5255121,0.05606867,0.397253,0.0004059318,0.002110985,0.001026572,0.01501528,0.0006730448,0.001934416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02162341,"threshold_uncertainty_score":0.1143569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4952072856871249,"score_gpt":0.4730338297708425,"score_spread":0.02217345591628234,"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."}}