{"id":"W3180273654","doi":"10.2139/ssrn.3708327","title":"Trends in COVID-19 Publications: Streamlining Research Using NLP and LDA","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Trinity College","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Natural language processing; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Artificial intelligence; 2019-20 coronavirus outbreak; Computer science; Medicine; Virology","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":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0128474,0.0006973754,0.001175858,0.06102451,0.00139081,0.01286367,0.001375007,0.001337823,0.006560401],"category_scores_gemma":[0.07479209,0.0004640713,0.001371214,0.07684485,0.0009209566,0.009276573,0.002851081,0.002135954,0.006651492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002097873,"about_ca_system_score_gemma":0.006129842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008364301,"about_ca_topic_score_gemma":0.01205385,"domain_scores_codex":[0.9884462,0.00216016,0.002414424,0.002072307,0.00428918,0.0006177535],"domain_scores_gemma":[0.8858846,0.05798789,0.01376037,0.005933037,0.03199306,0.004441014],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005276669,0.0002119021,0.2484543,0.005801583,0.0004396603,0.0003528563,0.0052178,0.001444521,0.005038493,0.01529703,0.1040374,0.6131768],"study_design_scores_gemma":[0.0001197643,0.000398304,0.4218209,0.003770186,0.000946842,0.00126978,0.01155212,0.01765857,0.008869709,0.020052,0.5133393,0.0002024724],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4539925,0.1250217,0.04953444,0.04933109,0.00654657,0.0009297848,0.208493,0.007565744,0.09858512],"genre_scores_gemma":[0.6894463,0.06187515,0.0647916,0.003072346,0.006333028,0.0009484849,0.1539824,0.002370436,0.01718029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9871526,"threshold_uncertainty_score":0.06794441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1657803183038663,"score_gpt":0.4051460986215873,"score_spread":0.239365780317721,"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."}}