{"id":837,"date":"2021-09-08T11:25:31","date_gmt":"2021-09-08T15:25:31","guid":{"rendered":"https:\/\/magazine.alumni.ncsu.edu\/?p=837"},"modified":"2024-02-01T15:39:22","modified_gmt":"2024-02-01T20:39:22","slug":"turning-to-twitter","status":"publish","type":"post","link":"https:\/\/magazine.ncsu.edu\/2021\/turning-to-twitter\/","title":{"rendered":"Turning to Twitter"},"content":{"rendered":"\n<h4 class=\"wp-block-heading\">By Ramona Dubose<\/h4>\n\n\n\n<p class=\"is-style-lead\">NC&#160;State researchers in the Poole College of Management are mining data from Twitter\u2009\u2014\u2009using keywords that correspond to symptoms\u2009\u2014\u2009to predict COVID-19 out-breaks, and have teamed up with the Clinton Health Access Initiative to predict hotspots in sub-Saharan Africa.<\/p>\n\n\n\n<p>The results in the U.S. have been accurate more often than 24 other models, most of which rely on reports of prior cases, deaths and additional medical surveillance and survey results. The predictions are collected and reported by the CDC. Associate Professor William Rand, executive director of the college\u2019s Business Analytics Initiative, is leading the team that is building and using models that rely on keywords in tweets, analyzing how often people mention two or more symptoms of COVID-19 to predict future COVID-19 outbreaks.<\/p>\n\n\n\n<p>The tweets must list at least two words that the World Health Organization has identified as COVID-19 symptoms, such as fever, headache or chill. To improve the search, they included partial spellings and combinations of words, such as \u201clos\u201d AND \u201ctaste\u201d, \u201clos\u201d AND \u201csmell,\u201d picking up phrases like \u201clost ability to taste,\u201d and \u201closing my sense of smell.\u201d<\/p>\n\n\n\n<p>Rand and his team used tweets from all 50 states for their predictions, and in comparisons with 24 other models developed at other institutions, NC&#160;State\u2019s models most closely predicted outcomes more than 30% of the time. In comparison, the next most accurate models\u2009\u2014\u2009which included those from Johns Hopkins and UCLA\u2009\u2014\u2009were correct only about 12 percent of the time.<\/p>\n\n\n\n<aside class=\"wp-block-ncst-sandwich-narrative\"><div class=\"ncst-sandwich-narrative\"><div class=\"sandwich-narrative__text-container\"><h2 class=\"sandwich-narrative__heading\">Pandemic Pulse<\/h2>\n\n<p><strong>Researchers are tracing the not-so-obvious effects of COVID-19 on the lives of students.<\/strong><\/p>\n\n\n\n\n<div class=\"wp-block-ncst-collapsible-more ncst-collapsible-more\"><div class=\"collapsible-more__collapsed-content-container collapse panel-collapse \" id=\"collapsible-more-0\" aria-labelledby=\"collapsible-more-heading-0\">\n<p>NC&#160;State and N.C. A&amp;T State University are collaborating to study the impact COVID-19 is having on its undergraduate engineering students.<\/p>\n\n\n\n<p>\u201cCollege students\u2019 well-being has been an important issue for a while, but with COVID it\u2019s more important,\u201d says Julie Ivy, a professor in the Edward P. Fitts Department of Industrial and Systems Engineering. \u201cNow they have the stress of not having social interaction. We want to see the effect it\u2019s had on them.\u201d<\/p>\n\n\n\n<p>The 105 students who have joined the study so far (the goal is to have 200 students from each university in the ongoing study) are asked weekly about their well-being, depression, their needs, any food insecurities and their sense of belonging. They are also questioned about their workload, including how they are adapting to classes taught online.<\/p>\n\n\n\n<p>\u201cWe need to be better prepared the next time there is a disruptive event like COVID,\u201d says Lauren Davis \u201905 phd, an engineering professor at N.C. A&amp;T. \u201cNot only do students have to adapt, we need to know how we can better support them in the classroom.\u201d<\/p>\n\n\n\n<p>Davis and Ivy, the principal investigators for the study, focused on engineering students because they had better access to them. \u201cThose are the students we teach,\u201d Davis says, noting that they were still collecting data this summer. \u201cWe want to see their responses,\u201d Ivy says, \u201ctheir basic needs, emotional well-being and their sense of belonging.\u201d <em>\u2014 Bridgette A. Lacy<\/em><\/p>\n<\/div><a class=\"collapsible-more__interaction-cta collapsed\" href=\"#collapsible-more-0\" id=\"collapsible-more-heading-0\" data-toggle=\"collapse\" data-target=\"#collapsible-more-0\" aria-controls=\"collapsible-more-0\"><span class=\"collapsible-more__expansion-indicator\"><span class=\"ncst-plus-minus-toggle\"><\/span><\/span><span class=\"collapsible-more__text\">Expand to read more<\/span><span class=\"collapsible-more__text-collapse\">Collapse<\/span><\/a><\/div>\n<\/div><\/div><\/aside>\n\n\n\n<p>Two of Rand\u2019s students, Aidan McCarthy and Trevor Ferree \u201920, came up with the models at the outset of the pandemic, and they\u2019re optimistic about the potential. \u201cWe&#8217;ve seen that social media data can provide results as good or better than conventional methods on a limited basis,\u201d McCarthy says. He cautions that the model has not been tested widely, and most of the testing occurred when tweets about COVID-19 symptoms were common.<\/p>\n\n\n\n<p>The partnership with the Clinton Health Access Initiative (CHAI), combines results from Twitter data with information gleaned from LexisNexis (news reports) and PubMed (biomedical and life sciences journal articles) to better understand needs. By \u201clistening\u201d to people\u2019s concerns, organizations like CHAI can \u201cmake time-sensitive resource allocation decisions,\u2019\u2019 says Paul Domanico, senior director of global health sciences at CHAI, \u201cas well as monitor the mental health of nurses and doctors participating in the COVID-19 response.\u201d To monitor mental health concerns, NC&#160;State researchers analyzed tweets from people in Kenya who self-identified as health care providers and used key words such as \u201cdepression,\u201d or \u201cdepressed.\u201d<\/p>\n\n\n\n<p>Until the pandemic, Rand\u2019s research focused on business applications for his models. But the collaboration with CHAI shows that analyzing big data could play a role in improving public health. \u201cIf we can apply these analyses to spreading public health knowledge and best practices,\u201d he says, \u201cit could be transformational.\u201d<\/p>\n","protected":false,"raw":"<!-- wp:ncst\/dynamic-header -->\n<!-- wp:ncst\/default-immersive-post-header \/-->\n<!-- \/wp:ncst\/dynamic-header -->\n\n<!-- wp:heading {\"level\":4} -->\n<h4>By Ramona Dubose<\/h4>\n<!-- \/wp:heading -->\n\n<!-- wp:paragraph {\"className\":\"is-style-lead\"} -->\n<p class=\"is-style-lead\">NC State researchers in the Poole College of Management are mining data from Twitter\u2009\u2014\u2009using keywords that correspond to symptoms\u2009\u2014\u2009to predict COVID-19 out-breaks, and have teamed up with the Clinton Health Access Initiative to predict hotspots in sub-Saharan Africa.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p>The results in the U.S. have been accurate more often than 24 other models, most of which rely on reports of prior cases, deaths and additional medical surveillance and survey results. The predictions are collected and reported by the CDC. Associate Professor William Rand, executive director of the college\u2019s Business Analytics Initiative, is leading the team that is building and using models that rely on keywords in tweets, analyzing how often people mention two or more symptoms of COVID-19 to predict future COVID-19 outbreaks.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p>The tweets must list at least two words that the World Health Organization has identified as COVID-19 symptoms, such as fever, headache or chill. To improve the search, they included partial spellings and combinations of words, such as \u201clos\u201d AND \u201ctaste\u201d, \u201clos\u201d AND \u201csmell,\u201d picking up phrases like \u201clost ability to taste,\u201d and \u201closing my sense of smell.\u201d<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p>Rand and his team used tweets from all 50 states for their predictions, and in comparisons with 24 other models developed at other institutions, NC State\u2019s models most closely predicted outcomes more than 30% of the time. In comparison, the next most accurate models\u2009\u2014\u2009which included those from Johns Hopkins and UCLA\u2009\u2014\u2009were correct only about 12 percent of the time.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:ncst\/sandwich-narrative {\"heading\":\"Pandemic Pulse\",\"useImage\":false} -->\n<aside class=\"wp-block-ncst-sandwich-narrative\"><div class=\"ncst-sandwich-narrative\"><div class=\"sandwich-narrative__text-container\"><h2 class=\"sandwich-narrative__heading\">Pandemic Pulse<\/h2><!-- wp:ncst\/text-heading-section -->\n<!-- wp:paragraph -->\n<p><strong>Researchers are tracing the not-so-obvious effects of COVID-19 on the lives of students.<\/strong><\/p>\n<!-- \/wp:paragraph -->\n<!-- \/wp:ncst\/text-heading-section -->\n\n<!-- wp:ncst\/collapsible-more {\"instanceID\":0} -->\n<div class=\"wp-block-ncst-collapsible-more ncst-collapsible-more\"><div class=\"collapsible-more__collapsed-content-container collapse panel-collapse \" id=\"collapsible-more-0\" aria-labelledby=\"collapsible-more-heading-0\"><!-- wp:paragraph -->\n<p>NC State and N.C. A&amp;T State University are collaborating to study the impact COVID-19 is having on its undergraduate engineering students.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p>\u201cCollege students\u2019 well-being has been an important issue for a while, but with COVID it\u2019s more important,\u201d says Julie Ivy, a professor in the Edward P. Fitts Department of Industrial and Systems Engineering. \u201cNow they have the stress of not having social interaction. We want to see the effect it\u2019s had on them.\u201d<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p>The 105 students who have joined the study so far (the goal is to have 200 students from each university in the ongoing study) are asked weekly about their well-being, depression, their needs, any food insecurities and their sense of belonging. They are also questioned about their workload, including how they are adapting to classes taught online.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p>\u201cWe need to be better prepared the next time there is a disruptive event like COVID,\u201d says Lauren Davis \u201905 phd, an engineering professor at N.C. A&amp;T. \u201cNot only do students have to adapt, we need to know how we can better support them in the classroom.\u201d<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p>Davis and Ivy, the principal investigators for the study, focused on engineering students because they had better access to them. \u201cThose are the students we teach,\u201d Davis says, noting that they were still collecting data this summer. \u201cWe want to see their responses,\u201d Ivy says, \u201ctheir basic needs, emotional well-being and their sense of belonging.\u201d <em>\u2014 Bridgette A. Lacy<\/em><\/p>\n<!-- \/wp:paragraph --><\/div><a class=\"collapsible-more__interaction-cta collapsed\" href=\"#collapsible-more-0\" id=\"collapsible-more-heading-0\" data-toggle=\"collapse\" data-target=\"#collapsible-more-0\" aria-controls=\"collapsible-more-0\"><span class=\"collapsible-more__expansion-indicator\"><span class=\"ncst-plus-minus-toggle\"><\/span><\/span><span class=\"collapsible-more__text\">Expand to read more<\/span><span class=\"collapsible-more__text-collapse\">Collapse<\/span><\/a><\/div>\n<!-- \/wp:ncst\/collapsible-more --><\/div><\/div><\/aside>\n<!-- \/wp:ncst\/sandwich-narrative -->\n\n<!-- wp:paragraph -->\n<p>Two of Rand\u2019s students, Aidan McCarthy and Trevor Ferree \u201920, came up with the models at the outset of the pandemic, and they\u2019re optimistic about the potential. \u201cWe've seen that social media data can provide results as good or better than conventional methods on a limited basis,\u201d McCarthy says. He cautions that the model has not been tested widely, and most of the testing occurred when tweets about COVID-19 symptoms were common.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p>The partnership with the Clinton Health Access Initiative (CHAI), combines results from Twitter data with information gleaned from LexisNexis (news reports) and PubMed (biomedical and life sciences journal articles) to better understand needs. By \u201clistening\u201d to people\u2019s concerns, organizations like CHAI can \u201cmake time-sensitive resource allocation decisions,\u2019\u2019 says Paul Domanico, senior director of global health sciences at CHAI, \u201cas well as monitor the mental health of nurses and doctors participating in the COVID-19 response.\u201d To monitor mental health concerns, NC State researchers analyzed tweets from people in Kenya who self-identified as health care providers and used key words such as \u201cdepression,\u201d or \u201cdepressed.\u201d<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p>Until the pandemic, Rand\u2019s research focused on business applications for his models. But the collaboration with CHAI shows that analyzing big data could play a role in improving public health. \u201cIf we can apply these analyses to spreading public health knowledge and best practices,\u201d he says, \u201cit could be transformational.\u201d<\/p>\n<!-- \/wp:paragraph -->"},"excerpt":{"rendered":"<p>Social media can provide some unexpected clues to help predict COVID-19 outbreaks.<\/p>\n","protected":false},"author":1,"featured_media":838,"comment_status":"open","ping_status":"open","sticky":false,"template":"views\/single-immersive.blade.php","format":"standard","meta":{"_acf_changed":false,"source":"","ncst_custom_author":"","ncst_show_custom_author":false,"ncst_dynamicHeaderBlockName":"ncst\/default-immersive-post-header","ncst_dynamicHeaderData":"{\"showAuthor\":false,\"showDate\":true,\"showFeaturedVideo\":false,\"backgroundColor\":\"indigo_400\",\"subtitle\":\"Social media can provide some unexpected clues to help predict COVID-19 outbreaks.\",\"displayCategoryID\":5,\"caption\":\"\"}","ncst_content_audit_freq":"","ncst_content_audit_date":"","footnotes":""},"categories":[9],"tags":[286,959,974,986,1264],"_ncst_magazine_issue":[],"class_list":["post-837","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-stories","tag-covid-19","tag-poole-college-of-management","tag-ramona-dubose","tag-research","tag-william-rand"],"displayCategory":{"term_id":5,"name":"Best Bets","slug":"best-bets","term_group":0,"term_taxonomy_id":5,"taxonomy":"category","description":"","parent":0,"count":52,"filter":"raw"},"acf":[],"_links":{"self":[{"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/posts\/837"}],"collection":[{"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/comments?post=837"}],"version-history":[{"count":1,"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/posts\/837\/revisions"}],"predecessor-version":[{"id":5065,"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/posts\/837\/revisions\/5065"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/media\/838"}],"wp:attachment":[{"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/media?parent=837"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/categories?post=837"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/tags?post=837"},{"taxonomy":"_ncst_magazine_issue","embeddable":true,"href":"https:\/\/magazine.ncsu.edu\/wp-json\/wp\/v2\/_ncst_magazine_issue?post=837"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}