{"id":"W4393423660","doi":"10.5281/zenodo.6523151","title":"Dataset: Characterizing Anti-Asian Rhetoric During The COVID-19 Pandemic: A Sentiment Analysis Case Study on Twitter","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Rhetoric; Coronavirus disease 2019 (COVID-19); Pandemic; Sentiment analysis; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; History; Computer science; Natural language processing; Linguistics; Virology; Biology; Medicine; Philosophy","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":[0.000719984,0.00135218,0.0005050443,0.001968718,0.0009699298,0.000881054,0.001202814,0.001696283,0.005463738],"category_scores_gemma":[0.00221887,0.0002056824,0.0006251613,0.001788232,0.0003574324,0.0007644708,0.001120056,0.0009800993,0.00826467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001190134,"about_ca_system_score_gemma":0.0008124905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01776486,"about_ca_topic_score_gemma":0.0459922,"domain_scores_codex":[0.9993775,0.0001305554,0.00009038219,0.0001188886,0.0001913147,0.00009125557],"domain_scores_gemma":[0.9988248,0.0003450267,0.0001387834,0.0001791792,0.0003716591,0.0001405281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0003455996,0.0004162388,0.01440424,0.001063338,0.00007521616,0.0005824898,0.0003546646,0.001790245,0.003650095,0.0008907156,0.9553425,0.02108467],"study_design_scores_gemma":[0.0005509105,0.0003405178,0.09113103,0.0003296761,0.0001071834,0.000970858,0.0020487,0.01758016,0.007793579,0.001804895,0.8771738,0.0001687528],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02619352,0.000244083,0.0008192909,0.0009325026,0.0002739475,0.0002326539,0.965888,0.001261769,0.004154351],"genre_scores_gemma":[0.01576704,0.0001180355,0.002351071,0.0002021254,0.00005928415,0.0003171683,0.9787319,0.00005706317,0.002396295],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01776486,"threshold_uncertainty_score":0.0353229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09524620877496874,"score_gpt":0.3257131129063965,"score_spread":0.2304669041314277,"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."}}