{"id":"W3185919331","doi":"10.22215/etd/2021-14497","title":"Tales of a Coronavirus Pandemic: Topic Modelling with Short-Text Data","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Term (time); Coronavirus disease 2019 (COVID-19); Natural language processing; Information retrieval; Pandemic; Artificial intelligence; Data science; Medicine","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":[0.004890813,0.0005960958,0.0005360605,0.002560201,0.0007076939,0.002589388,0.0007983391,0.001244603,0.001695954],"category_scores_gemma":[0.01954673,0.0004402538,0.001099756,0.002480868,0.0005775647,0.003263726,0.0009043068,0.00240022,0.0008544311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008428528,"about_ca_system_score_gemma":0.000622982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005607553,"about_ca_topic_score_gemma":0.005666941,"domain_scores_codex":[0.9987718,0.000703593,0.00006336747,0.0002053386,0.0001945921,0.00006134446],"domain_scores_gemma":[0.9821217,0.01594828,0.0005623182,0.0005274934,0.0006114994,0.0002287296],"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":[0.001035363,0.0006140769,0.06828276,0.001202076,0.0008111995,0.000932947,0.008822118,0.3693289,0.00526064,0.02839311,0.02625015,0.4890667],"study_design_scores_gemma":[0.00002998019,0.0001449757,0.02082649,0.0001461002,0.0001121629,0.0001888273,0.001852009,0.920027,0.001734281,0.04196782,0.01288667,0.00008379464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5790862,0.01134527,0.3814184,0.01130197,0.0005255608,0.0004176772,0.005490657,0.001168051,0.009246206],"genre_scores_gemma":[0.8744115,0.004562788,0.1085992,0.0003991317,0.0006579937,0.0002491693,0.005854692,0.0001483604,0.005117134],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005607553,"threshold_uncertainty_score":0.02586544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1563107601503418,"score_gpt":0.3371977118474921,"score_spread":0.1808869516971502,"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."}}