{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003213244,0.0001283109,0.0001683891,0.00005328816,0.0005896759,0.0008411537,0.0002370782,0.00005070172,0.00006111141],"category_scores_gemma":[0.00007683649,0.0001250291,0.00009497877,0.0005226973,0.00004424778,0.0004644608,0.000430524,0.00008152564,0.000002208624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381385,"about_ca_system_score_gemma":0.0003324414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001626808,"about_ca_topic_score_gemma":0.000002605312,"domain_scores_codex":[0.9986919,0.00005614614,0.0001832479,0.000402374,0.0002762721,0.0003900401],"domain_scores_gemma":[0.9991955,0.00004545287,0.00006988117,0.0003047645,0.0001904048,0.0001940669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003466964,0.0006888677,0.07986647,0.004543508,0.0004516461,0.0007621719,0.2067345,0.007870711,0.001344597,0.008945659,0.6585776,0.03017955],"study_design_scores_gemma":[0.002595586,0.0001067156,0.006801285,0.0001335494,0.0001240751,0.00001060987,0.417745,0.4089782,0.001239739,0.00107147,0.1599685,0.001225385],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5916761,0.0009253192,0.4046579,0.001965797,0.0001454343,0.0002336627,0.00006875259,0.00009968672,0.0002272704],"genre_scores_gemma":[0.9226457,0.00002708505,0.04802317,0.02510437,0.0001366629,0.00001909488,0.0008612505,0.00002276171,0.003159864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4986092,"threshold_uncertainty_score":0.8111265,"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."}}