{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008143571,0.0001866109,0.0005150767,0.0002693822,0.0001289249,0.0001933882,0.001897458,0.00008277502,0.000006203705],"category_scores_gemma":[0.000203823,0.0001986788,0.000125257,0.001581298,0.00004993823,0.0006698933,0.0005112023,0.0002082234,0.000003476748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008139008,"about_ca_system_score_gemma":0.00008792921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008640205,"about_ca_topic_score_gemma":0.0000527215,"domain_scores_codex":[0.99764,0.0001809818,0.0006668121,0.0009436798,0.0001881166,0.000380419],"domain_scores_gemma":[0.9986843,0.0001289878,0.00008131285,0.0008696752,0.0001037103,0.0001320452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001909972,0.00002711432,0.0003334781,0.0000127984,0.0001158105,0.000002710711,0.003538098,0.7611758,0.0003489654,0.01483607,0.0000474457,0.2195426],"study_design_scores_gemma":[0.00001658262,0.00002225441,0.000002548848,0.00000953354,0.00007522258,4.257576e-7,0.0008918464,0.9730126,0.002803313,0.02269005,0.0002654483,0.000210233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002544735,0.0005148146,0.9950877,0.0005668722,0.0007657738,0.0003391464,0.000008272566,0.00007679546,0.00009591894],"genre_scores_gemma":[0.3765037,0.000008768868,0.6231927,0.0001667282,0.0001024207,0.00001036344,0.000007168841,0.000004771419,0.000003425973],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3739589,"threshold_uncertainty_score":0.8101886,"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."}}