{"id":"W7165199962","doi":"10.6082/6bp61-11w10","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":"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"],"consensus_categories":[],"category_scores_codex":[0.0007731141,0.00006405744,0.0001155291,0.00009485895,0.001744747,0.00003135619,0.0003324439,0.00003691027,0.0007039542],"category_scores_gemma":[0.0003357718,0.00004926526,0.0001359358,0.0008752139,0.0002052205,0.00007567359,0.0001413757,0.000141487,0.00007399813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001343597,"about_ca_system_score_gemma":0.000112015,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01076034,"about_ca_topic_score_gemma":0.006903044,"domain_scores_codex":[0.9986849,0.0005518071,0.00009174377,0.0001676801,0.0003304774,0.0001733256],"domain_scores_gemma":[0.9987146,0.0009112843,0.00009847758,0.00010842,0.00005547918,0.0001117039],"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":[0.0001195982,0.00006064388,0.181319,0.00003276128,0.0003781614,0.00002410317,0.5598298,0.2076568,0.001767493,0.003357277,0.003600827,0.04185359],"study_design_scores_gemma":[0.0007277699,0.00003177462,0.08683677,0.00002213378,0.0002090961,0.000003050441,0.2452014,0.02242686,0.00006904105,0.005576541,0.6385898,0.0003058031],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97045,0.00002096528,0.007861045,0.01761395,0.00004807688,0.0001678374,0.000002658874,0.00007580856,0.003759596],"genre_scores_gemma":[0.9868872,0.00009511459,0.001388995,0.0006546144,0.0001074207,1.987114e-7,0.000002017576,0.000005083267,0.01085939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.634989,"threshold_uncertainty_score":0.9995549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07815302857687048,"score_gpt":0.3475239700143952,"score_spread":0.2693709414375247,"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."}}