{"id":"W4385552004","doi":"10.1017/s1351324923000396","title":"SSL-GAN-RoBERTa: A robust semi-supervised model for detecting Anti-Asian COVID-19 hate speech on social media","year":2023,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Social media; Transformer; Artificial intelligence; Task (project management); Coronavirus disease 2019 (COVID-19); Machine learning; Speech recognition; Data mining; Voltage","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004007425,0.0002739129,0.0002585098,0.0003543282,0.000314911,0.0002034962,0.0005400122,0.0001819483,0.000005987353],"category_scores_gemma":[0.0008428596,0.0002688793,0.0001652033,0.0008738369,0.00001248373,0.0003391003,0.0001033014,0.0004655428,0.00004077297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001806447,"about_ca_system_score_gemma":0.00005917796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004041855,"about_ca_topic_score_gemma":0.00007405132,"domain_scores_codex":[0.9982157,0.00002435894,0.0002374035,0.0005071966,0.0003585649,0.0006567381],"domain_scores_gemma":[0.9991056,0.0002823913,0.00006068651,0.0003040315,0.00005043745,0.0001968817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004146578,0.00003219948,0.000011109,0.0003211481,0.00008234035,0.0003783641,0.02176809,0.6729297,0.1386705,0.001161449,0.001602658,0.163001],"study_design_scores_gemma":[0.0005442609,0.00002050402,0.00009802294,0.00003279547,0.000009387298,0.00002775181,0.0002866216,0.9804564,0.01796244,0.0000442294,0.0001847843,0.0003327868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.447977,0.0002678077,0.5452021,0.001004449,0.00194343,0.0004973617,0.00002713547,0.002951778,0.0001289004],"genre_scores_gemma":[0.9770392,0.000006530949,0.02184563,0.0002365069,0.0005002445,0.00004301398,0.00003406005,0.00004925767,0.0002455405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5290622,"threshold_uncertainty_score":0.9999763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0259402050914098,"score_gpt":0.260374998053483,"score_spread":0.2344347929620732,"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."}}