{"id":"W4309776725","doi":"10.1007/s00146-022-01594-w","title":"Natural language processing analysis applied to COVID-19 open-text opinions using a distilBERT model for sentiment categorization","year":2022,"lang":"en","type":"article","venue":"AI & Society","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Universidad de Deusto","keywords":"Sentiment analysis; Categorization; Recall; Computer science; Natural language processing; Coronavirus disease 2019 (COVID-19); Task (project management); Artificial intelligence; Precision and recall; Feeling; F1 score; Data science; Machine learning; Psychology; Cognitive psychology; Social psychology; Infectious disease (medical specialty); Disease; Engineering; Medicine","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005171669,0.0001601558,0.0002789292,0.0001180137,0.001322499,0.0005356786,0.0009304878,0.00003107519,0.00004096646],"category_scores_gemma":[0.0000158638,0.0001629074,0.0003317335,0.002097485,0.00001825883,0.0003372105,0.001061963,0.0001245658,0.000002231909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004013132,"about_ca_system_score_gemma":0.0002910148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001748601,"about_ca_topic_score_gemma":0.00002799614,"domain_scores_codex":[0.998324,0.00004181094,0.0002991097,0.0006186463,0.0004048792,0.0003115552],"domain_scores_gemma":[0.9991608,0.0000515495,0.0001727325,0.0003874274,0.00006735797,0.0001601355],"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":[0.00001223366,0.000127165,0.0003233104,0.00002707136,0.0004615544,7.693397e-7,0.03756674,0.9418431,0.001386465,0.005851786,0.00828316,0.004116635],"study_design_scores_gemma":[0.0003897474,0.00001462616,0.00004247731,0.00000244414,0.0002018823,0.000001091651,0.002585248,0.994711,0.00006404602,0.000186066,0.001580022,0.0002213596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003724372,0.0001565038,0.9929639,0.002368894,0.0001205696,0.0005053252,0.00002765861,0.00007446534,0.00005830857],"genre_scores_gemma":[0.8892415,0.000001532185,0.1033024,0.006054206,0.00004750225,0.0001907429,0.0004506702,0.00001402276,0.0006974746],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8896615,"threshold_uncertainty_score":0.9999776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04092020058568206,"score_gpt":0.357378175119517,"score_spread":0.3164579745338349,"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."}}