{"id":"W3164920349","doi":"10.1016/j.scs.2021.103048","title":"n-Gram based language processing using Twitter dataset to identify COVID-19 patients","year":2021,"lang":"en","type":"article","venue":"Sustainable Cities and Society","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; Seneca Polytechnic","funders":"Alfaisal University","keywords":"Coronavirus disease 2019 (COVID-19); n-gram; Gram; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Computer science; Natural language processing; Artificial intelligence; Medicine; Language model; Virology; Biology; Pathology; Outbreak","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":[0.0005168213,0.0005127603,0.0003976497,0.001452384,0.0004393606,0.0006625203,0.0003057092,0.0004932866,0.003072202],"category_scores_gemma":[0.002450394,0.00007675528,0.0005771844,0.00100305,0.0001177411,0.0004345957,0.0005166291,0.0004777671,0.002378863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004708722,"about_ca_system_score_gemma":0.0008272104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005536359,"about_ca_topic_score_gemma":0.0106397,"domain_scores_codex":[0.9994776,0.0001095891,0.00008037125,0.00008818658,0.0001366645,0.0001076003],"domain_scores_gemma":[0.9989857,0.000356352,0.0001551947,0.0000466881,0.0003478761,0.0001082093],"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":[0.003596955,0.001226436,0.3487522,0.001107786,0.0004186797,0.002969834,0.001371904,0.00656184,0.03850881,0.001822466,0.1404451,0.4532181],"study_design_scores_gemma":[0.0002328056,0.001594635,0.4208364,0.0003069099,0.000607821,0.003724364,0.009204826,0.4459927,0.02824644,0.006828401,0.08220503,0.0002196696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8510942,0.001227854,0.03639241,0.004161242,0.0008594057,0.0009279966,0.0886138,0.002641309,0.01408173],"genre_scores_gemma":[0.8952859,0.000534457,0.03531511,0.0006271719,0.0004670922,0.0004598182,0.06109209,0.00009396814,0.006124265],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005536359,"threshold_uncertainty_score":0.01100826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02893489579678772,"score_gpt":0.3423196018229588,"score_spread":0.3133847060261711,"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."}}