{"id":"W6976840131","doi":"10.6082/uchicago.6033","title":"Is the News Always Negative? Using Deep Learning to Track News Sentiment During the Covid-19 Pandemic","year":2023,"lang":"en","type":"article","venue":"Knowledge@UChicago (University of Chicago)","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"News media; Politics; Pandemic; News values; Coronavirus disease 2019 (COVID-19); Topic model; News analytics; Focus (optics); Sentiment analysis","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001748524,0.0001842495,0.0003173984,0.0002761378,0.003643136,0.00007681025,0.0008728398,0.0001180359,0.001499047],"category_scores_gemma":[0.0008111083,0.0001509531,0.0003569228,0.002453124,0.0004795301,0.0001791559,0.0004179603,0.0004271661,0.0004666182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002899025,"about_ca_system_score_gemma":0.0003428893,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005808947,"about_ca_topic_score_gemma":0.02404253,"domain_scores_codex":[0.9969203,0.001414334,0.0002317335,0.0004424885,0.0005517834,0.0004393334],"domain_scores_gemma":[0.9969519,0.00200532,0.0002269059,0.000306598,0.000189776,0.0003195172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002182541,0.000232164,0.05834396,0.0001179725,0.000733349,0.00003083211,0.7785542,0.04129066,0.002342443,0.005836499,0.007016792,0.1052829],"study_design_scores_gemma":[0.001341103,0.00006952368,0.07158656,0.00006239582,0.0004253015,0.000009195181,0.2120073,0.03932542,0.00007381872,0.009202388,0.6652364,0.0006606532],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9550608,0.0001687558,0.008897022,0.02236903,0.0001908022,0.0004840038,0.000008735653,0.0002440919,0.01257678],"genre_scores_gemma":[0.9800712,0.0002157012,0.001609217,0.0004253395,0.0003043427,0.000001613828,0.000006095044,0.00001822318,0.01734823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6582196,"threshold_uncertainty_score":0.9994137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08298298068602979,"score_gpt":0.3561609718017648,"score_spread":0.273177991115735,"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."}}