[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126657-en":3,"doc-seo-126657-105":29,"detail-sidebar-cat-0-en-105":89},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":11},126657,549768064778,"Finn","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Emotional Distress During COVID-19 by Mental Health Conditions and Economic Vulnerability - Retrospective Analysis of Survey-Linked Twitter Data With a Semisupervised Machine Learning Algorithm","Research to Practice brief analyzing how emotional distress shifted during COVID-19 across the first pandemic year in Japan using survey-linked Twitter data collected in 2020 with participant consent. A latent semantic scaling (LSS) approach quantifies emotional distress by estimating the polarity of words and emojis via seed words for distinct emotional states, then maps scores to key 2020 events, using 2019 as a baseline. Findings show demographic variation, with government measures linked to greater mental health harm than infection spread, and highlight continuous monitoring potential via social media.","Syracuse University  \nSURFACE at Syracuse University  \n\n| Center for Policy Design and Governance | Institutes, Research Centers, and Campus Groups |\n| --- | --- |\n| Summer 8-18-2023\u003Cbr>Emotional Distress During COVID-19 by Mental Health Conditions and Economic Vulnerability: Retrospective Analysis of Survey-Linked Twitter Data With a Semisupervised Machine Learning Algorithm\u003Cbr>Michiko Ueda-Ballmer\u003Cbr>Syracuse University, [mueda@syr.edu](mueda@syr.edu)\u003Cbr>Kohei Watanabe Waseda University\u003Cbr>Hajime Sueki Wako University\u003Cbr>Davor Mondom\u003Cbr>rllaocwuiinvrt,itdionl omrk:rhets://surface.syr.edu/cpdg\u003Cbr> Part of the Emergency and Disaster Management Commons, Health Policy Commons, Policy Design, Analysis, and Evaluation Commons, Public Administration Commons, Public Affairs Commons, Public Policy Commons, Science and Technology Policy Commons, Social Policy Commons, and the Social Welfare Commons |  |\n\nRecommended Citation  \nUeda-Ballmer, Michiko; Watanabe, Kohei; Sueki, Hajime; and Mondom, Davor, \"Emotional Distress During COVID-19 by Mental Health Conditions and Economic Vulnerability: Retrospective Analysis of SurveyLinked Twitter Data With a Semisupervised Machine Learning Algorithm\" (2023) . Center for Policy Design and Governance. 2.  \n[https://surface.syr.edu/cpdg/2](https://surface.syr.edu/cpdg/2)  \nThis Research Brief is brought to you for free and open access by the Institutes, Research Centers, and Campus Groups at SURFACE at Syracuse University. It has been accepted for inclusion in Center for Policy Design and Governance by an authorized administrator of SURFACE at Syracuse University. For more information, please contact [surface@syr.edu](surface@syr.edu).  \nAugust 2023 Research to Practice Brief \\#: 2  \nEmotional Distress During COVID-19 by Mental Health Conditions and Economic Vulnerability: Retrospective Analysis of Survey-Linked Twitter Data With a Semisupervised Machine Learning Algorithm  \n(Michiko Ueda, Kohei Watanabe, Hajime Sueki)  \nBrief Author: DavorMondom  \nThis article uses survey-linked Twitter data from Japanese users from the year 2020 to trace changes in mental health conditions across the first year of the COVID-19 pandemic. With their consent, the authors retrieved the past tweets of the survey participants. An algorithm called latent semantic scaling (LSS) quantified emotional distress levels for those surveyed by estimating the polarity of words as well as emojis used in their tweets. It did so by assigning a numerical score based on the similarities between the language and emojis in the tweets and a set of \"seed words\" that signaled different emotional states. These were then mapped across specific events in 2020, including the abrupt closure of schools in March and the declaration of a state of emergency in April. 2019 was used asa baseline year.  \nKEY FINDINGS  \n• Emotional distress levels in response to the COVID-19 pandemic varied across demographic categories such as gender, socio-economic status, and employment level.  \n• Government measures designed to combat COVID-19 hada greater negative impact on mental health than the spread of the disease itself.  \nThe Demographics of Mental Health During COVID-19  \nThe authors found that the effect of the COVID-19 pandemic on mental health varied across demographic groups. Women saw their emotional distress levels increase more than men when schools closed in early March, though the state of emergency seemed to affect both women and men fairly equally. Those with secure employment had less emotional distress during the state of emergency than those whose jobs were insecure or the unemployed. The largest disparities were seen along the socioeconomic dimension. Low-income individuals saw their emotional distress soar and stay high for several months after lockdown was first imposed, whereas higher-income individuals only had a modest increase that did not persist. This analysis reveals that populations already suffering some form of disadvantage were m","cbCainoNQpS474hO","https://ap.wps.com/l/cbCainoNQpS474hO","pdf",487730,1,3,"English","en",105,"# Key Findings\n## Demographics of Mental Health During COVID-19\n## Factors Impacting Mental Health During COVID-19\n# Method Overview\n## Data and Consent\n## Latent Semantic Scaling (LSS) Algorithm\n# References and Author Background","[{\"question\":\"How was emotional distress measured in the study?\",\"answer\":\"The study used latent semantic scaling (LSS) to quantify emotional distress from survey-linked tweets by estimating the polarity of words and emojis relative to seed words representing different emotional states.\"},{\"question\":\"Which factors were most associated with changes in mental health during COVID-19?\",\"answer\":\"Emotional distress rose when government policies targeted to limit the spread of COVID-19 were enacted (e.g., closing schools or travel restrictions), while there was no correlation with the number of positive COVID-19 cases.\"},{\"question\":\"How did emotional distress differ across demographic groups?\",\"answer\":\"Women reported larger increases than men when schools closed, secure employment was linked to lower distress than insecure or unemployed work, and the strongest disparities appeared by socioeconomic status, with low-income individuals sustaining higher distress for months.\"}]","Emotional Distress During COVID-19 by Mental Health Conditions and Economic Vulnerability - Retrospective Analysis of Survey-Linked Twitter Data With a Semisupervised Machine Learning Algorithm | PDF",1785934068,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":28},"emotional-distress-during-covid-19-by-mental-health-conditions-and-economic-vulnerability-retrospective-analysis-of-survey-linked-twitter-data-with-a-semisupervised-machine-learning-algorithm","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":21},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/emotional-distress-during-covid-19-by-mental-health-conditions-and-economic-vulnerability-retrospective-analysis-of-survey-linked-twitter-data-with-a-semisupervised-machine-learning-algorithm/126657/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"How was emotional distress measured in the study?","Question",{"text":73,"@type":74},"The study used latent semantic scaling (LSS) to quantify emotional distress from survey-linked tweets by estimating the polarity of words and emojis relative to seed words representing different emotional states.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"Which factors were most associated with changes in mental health during COVID-19?",{"text":78,"@type":74},"Emotional distress rose when government policies targeted to limit the spread of COVID-19 were enacted (e.g., closing schools or travel restrictions), while there was no correlation with the number of positive COVID-19 cases.",{"name":80,"@type":71,"acceptedAnswer":81},"How did emotional distress differ across demographic groups?",{"text":82,"@type":74},"Women reported larger increases than men when schools closed, secure employment was linked to lower distress than insecure or unemployed work, and the strongest disparities appeared by socioeconomic status, with low-income individuals sustaining higher distress for months.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]