{"id":"W4206141885","doi":"10.2196/32449","title":"Using Natural Language Processing to Explore Mental Health Insights From UK Tweets During the COVID-19 Pandemic: Infodemiology Study","year":2022,"lang":"en","type":"article","venue":"JMIR Infodemiology","topic":"Mental Health via Writing","field":"Psychology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Department of Health and Social Care; National Institute for Health and Care Research","keywords":"Social media; Sentiment analysis; Mental health; Social distance; Pandemic; Coronavirus disease 2019 (COVID-19); Computer science; Set (abstract data type); Artificial intelligence; Data science; Natural language processing; Psychology; Medicine; World Wide Web; Psychiatry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002339581,0.0002356363,0.0001899953,0.002951556,0.0007691182,0.001536295,0.0003741892,0.0008803583,0.001599645],"category_scores_gemma":[0.01752026,0.0002066495,0.0004150478,0.002600504,0.001085548,0.001783265,0.001414392,0.0005873233,0.0004558373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001616988,"about_ca_system_score_gemma":0.0009272705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01375982,"about_ca_topic_score_gemma":0.01839527,"domain_scores_codex":[0.9981654,0.000998428,0.0001881797,0.0002369633,0.0002243791,0.0001867231],"domain_scores_gemma":[0.9812344,0.01410038,0.002453149,0.0006711142,0.001225562,0.0003154302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001100212,0.0007774383,0.7717072,0.002230628,0.0002029185,0.006833188,0.08874895,0.001850855,0.008046873,0.004224676,0.009249656,0.1050274],"study_design_scores_gemma":[0.0000732658,0.0005943062,0.8610072,0.0007718853,0.0001521914,0.002262435,0.08347587,0.01264188,0.004050701,0.002711153,0.03214366,0.0001154604],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99192,0.0004351987,0.001852173,0.001198508,0.00002485692,0.0002105834,0.002100214,0.00002079371,0.002237672],"genre_scores_gemma":[0.9930502,0.0005747779,0.003193966,0.0004154788,0.00006379317,0.0002372852,0.00171854,0.00001667482,0.0007293105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01375982,"threshold_uncertainty_score":0.02735949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2183885645283232,"score_gpt":0.5021741650179332,"score_spread":0.28378560048961,"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."}}