{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001111491,0.0006041062,0.0003234787,0.001391802,0.0003622926,0.001082324,0.0004951183,0.0006395019,0.002296244],"category_scores_gemma":[0.003123738,0.0001275308,0.0007955225,0.0005511474,0.0001814008,0.0008240659,0.0003599713,0.0009059112,0.001267972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001083184,"about_ca_system_score_gemma":0.0005043549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007875835,"about_ca_topic_score_gemma":0.008257731,"domain_scores_codex":[0.9995942,0.00013853,0.00003966505,0.00009197255,0.00008503881,0.00005057774],"domain_scores_gemma":[0.9984171,0.000919815,0.00009156791,0.00006752175,0.0004545631,0.00004940138],"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":[0.001491253,0.001528244,0.04283211,0.0005350549,0.0004559238,0.00108256,0.001306037,0.1708947,0.05963231,0.006750064,0.02085297,0.6926389],"study_design_scores_gemma":[0.000008880159,0.00006630302,0.003389222,0.000009575333,0.00002557219,0.00003955636,0.00009667018,0.9907674,0.003549969,0.001192147,0.0008454595,0.000009185011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.673036,0.0005251263,0.310889,0.001926791,0.0002607703,0.0004547975,0.003307762,0.003192358,0.006407422],"genre_scores_gemma":[0.9425476,0.0001320715,0.05223681,0.000132017,0.00007957888,0.0001036136,0.002285725,0.00004072333,0.002441811],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007875835,"threshold_uncertainty_score":0.01565999,"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."}}