{"id":218762,"date":"2017-02-20T16:22:58","date_gmt":"2017-02-20T21:22:58","guid":{"rendered":"http:\/\/www.rochester.edu\/newscenter\/?p=218762"},"modified":"2024-10-29T15:15:02","modified_gmt":"2024-10-29T19:15:02","slug":"what-twitter-and-data-science-tell-us-about-the-2016-election-218762","status":"publish","type":"post","link":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/","title":{"rendered":"Twitter researchers offer clues for why Trump won"},"content":{"rendered":"<p>Jiebo Luo and Yu Wang did not set out to predict who would win the 2016 U.S. presidential election. However, their exhaustive, 14-month study of each candidate\u2019s Twitter followers\u2013enabled by machine learning and other data science tools\u2013offers tantalizing clues as to why the race turned out the way it did.<\/p>\n<p><a href=\"http:\/\/www.rochester.edu\/news\/unlocking-big-data\/\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-220142 size-full\" style=\"border: none;\" src=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/dandelion-data-science-logo.jpg\" alt=\"illustration of dandelion with data as seeds\" width=\"400\" height=\"214\" \/><\/a><\/p>\n<h2 class=\"lighter\">Unlocking big data<\/h2>\n<p>&nbsp;<\/p>\n<h3 class=\"lighter\">A Newscenter series on how Rochester is using data science to change how we research, how we learn, and how we understand our world.<\/h3>\n<p>&nbsp;<\/p>\n<p>\u201cWe wanted to understand how each of the candidate\u2019s campaigns evolved, and be able to explain why someone won or lost,\u201d says Luo, an associate professor of computer science.<\/p>\n<p>Luo and Wang, a dual PhD candidate in political and computer science, summarized their findings in eight papers during the course of the campaign, including these observations:<\/p>\n<ul>\n<li>The more Donald Trump tweeted, the faster his following grew\u2013even after he performed poorly in debates against other Republican candidates, and even after he sparked controversies, such as proposing a ban on Muslim immigration. <strong><a href=\"https:\/\/arxiv.org\/abs\/1603.08174\">(Read the paper.)<\/a><\/strong><\/li>\n<li>When Trump accused Hillary Clinton of playing the \u201cwoman card,\u201d women were more likely to follow Clinton and less likely to \u201cun-follow\u201d her during the week that followed. But it did not affect the gender composition of Trump followers. <strong><a href=\"https:\/\/arxiv.org\/abs\/1605.05401\">(Read the paper.)<\/a><\/strong><\/li>\n<li>Moreover, a \u201cgender affinity effect\u201d seen in other elections\u2013women tending to vote for women\u2013did not appear to be working for Clinton as the primaries drew to a close. The percentage of female Twitter followers in the Clinton camp was no larger than that in the Trump camp. Moreover, though \u201cun-followers\u201d were more likely to be female for both candidates, the phenomenon was \u201cparticularly pronounced\u201d for Clinton. <strong><a href=\"https:\/\/arxiv.org\/abs\/1604.07103\">(Read the paper.)<\/a><\/strong><\/li>\n<li>At the same time, several polls, including ABC\/<em>Washington Post<\/em> and CBS\/<em>New York Times<\/em>, suggested that some Bernie Sanders supporters might \u201cjump ship\u201d from the Democratic column, and end up voting for Trump if Sanders dropped out. Luo and Wang found supporting evidence, reporting that the number of Bernie Sanders followers who were also following Trump was increasing\u2013but the number also following Clinton was declining. The dual Sanders\/Trump followers were also disproportionately (up to 64 percent) male. <strong><a href=\"https:\/\/arxiv.org\/abs\/1605.09473\">(Read the paper.)<\/a><\/strong><\/li>\n<\/ul>\n<p>\u201cIn the end, even though we chose not to make any predictions, we were not surprised at all that Donald Trump won,\u201d says Luo.<\/p>\n<h3>Why Twitter?<\/h3>\n<p>Barack Obama\u2019s use of social media in the 2008 presidential race helped establish Twitter and other social media platforms as powerful tools for candidates to quickly reach and receive feedback from large numbers of potential voters\u2013and to attack their opponents.<\/p>\n<p>Since then, there\u2019s been a burgeoning interest in scholarly research employing data science to analyze elections based on social media postings.<\/p>\n<p>Twitter, in particular, is a rich source of data because the millions of tweets posted by its members each day are easily accessible using an application programming interface.<\/p>\n<p>The key for Luo, Wang, and their colleagues was to collect as much of this data as possible, starting early in the campaign, and to then \u201cmine\u201d it in innovative ways.<\/p>\n<figure id=\"attachment_218782\" aria-describedby=\"caption-attachment-218782\" style=\"width: 630px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-218782\" src=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers-630x630.jpg\" alt=\"\" width=\"630\" height=\"630\" srcset=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers-630x630.jpg 630w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers-768x768.jpg 768w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers-1024x1024.jpg 1024w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers-32x32.jpg 32w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers-50x50.jpg 50w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers-64x64.jpg 64w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers-96x96.jpg 96w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers-128x128.jpg 128w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/gender-of-followers.jpg 1300w\" sizes=\"auto, (max-width: 630px) 100vw, 630px\" \/><figcaption id=\"caption-attachment-218782\" class=\"wp-caption-text\">Gender of candidate Twitter followers in April 2016, compiled by Wang and Luo.<\/figcaption><\/figure>\n<p>\u201cThe very nature of this data is that it will disappear tomorrow, so we had to start capturing it from an early stage and design a research framework so we could continue to collect data all along,\u201d said Wang.<\/p>\n<p>From September 2015 through October 2016, the team began accumulating a huge data set that included:<\/p>\n<ul>\n<li>The number of Twitter followers of each of the major candidates in the initially crowded field\u2013updated every 10 minutes.<\/li>\n<li>8 million tweets sampled from the followers of Clinton and Trump.<\/li>\n<li>1 million images of the candidates\u2019 followers on Twitter.<\/li>\n<li>5 million Twitter IDs that include all candidate followers in early April 2016.<\/li>\n<\/ul>\n<p>Using advanced computer vision tools, the researchers trained an artificial neural network (what&#8217;s called a convolutional neural network) to determine\u2013with 90 percent accuracy or more\u2013the age, gender, and race of the candidates\u2019 followers using their Twitter photos. This helped the researchers analyze the role of each of those factors in the campaign, as they tracked the changes in each candidate\u2019s followers before and after debates, for example, and how followers reacted to the candidates\u2019 own tweets.<\/p>\n<p>Twitter mining has its limits compared to the responses gleaned from traditional telephone polling. There\u2019s no opportunity to ask follow-up questions, for example, and tweets are difficult to place geographically, limiting their application for studying trends in swing states. (Even geotagged tweets may be sent while the sender is on vacation or attending a rally in another state.)<\/p>\n<p>But Twitter mining also has its advantages\u2013enabling researchers to quickly, continually, and inexpensively sample data on a scale that far surpasses the 1,000 or so responses that pollsters increasingly struggle to gather using traditional techniques. In one study, for example Luo and Wang were able to characterize 322,116 Trump or Clinton followers who subsequently became \u201cun-followers.\u201d<\/p>\n<figure id=\"attachment_218792\" aria-describedby=\"caption-attachment-218792\" style=\"width: 630px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-218792\" src=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/candidateFollowers-1-630x630.jpg\" alt=\"\" width=\"630\" height=\"630\" srcset=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/candidateFollowers-1-630x630.jpg 630w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/candidateFollowers-1-768x768.jpg 768w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/candidateFollowers-1-1024x1024.jpg 1024w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/candidateFollowers-1-32x32.jpg 32w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/candidateFollowers-1-50x50.jpg 50w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/candidateFollowers-1-64x64.jpg 64w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/candidateFollowers-1-96x96.jpg 96w, https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/candidateFollowers-1-128x128.jpg 128w\" sizes=\"auto, (max-width: 630px) 100vw, 630px\" \/><figcaption id=\"caption-attachment-218792\" class=\"wp-caption-text\">The candidates&#8217; shares of total Twitter candidate followers in April 2016. The unweighted tallies simply count the number of followers. The weighted tallies take into account the fact that one individual can follow more than one candidate. As an example, an individual following two candidates has only a weight of 1\/2, and an individual following three candidates has a weight of 1\/3. By avoiding double counting, the weighted metric could better measure candidates&#8217; influence.<\/figcaption><\/figure>\n<p>\u201cThis is an approach that is broadly applicable,\u201d Luo says. \u201cIf you want to test public reaction to the next generation of iPhones, or to a new model of car, you can use the same approach to see what consumers like or don\u2019t like. It enables us to track millions of people and get reliable readings on their preferences.\u201d<\/p>\n<p>Other Election 2016 papers by Luo, Wang, and their colleagues look at:<\/p>\n<ul>\n<li>\u00a0<a href=\"https:\/\/arxiv.org\/abs\/1611.02806\">Gender Politics . . . A Computer Vision Approach<\/a><\/li>\n<li>\u00a0<a href=\"https:\/\/arxiv.org\/abs\/1611.03168\">Inferring Voter Preferences . . . Using Sparse Learning<\/a><\/li>\n<li>\u00a0<a href=\"https:\/\/arxiv.org\/abs\/1603.03097\">A Comparison of Trumpists and Clintonists<\/a><\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1603.03099\">Inferring Topic Preferences of Trump Followers<\/a><\/li>\n<li>\u00a0<a href=\"https:\/\/arxiv.org\/abs\/1701.06250\">Rumor Detection<\/a><\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1701.06232\">Election Bias: Comparing Polls and Twitter<\/a>.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>The more Donald Trump tweeted, the faster his following grew, even after he sparked controversies. This is among the many findings from an exhaustive 14-month study of each candidate&#8217;s tweets during the 2016 election by researchers Jiebo Luo and Yu Wang.<\/p>\n","protected":false},"author":286,"featured_media":220192,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[456],"tags":[41372,11716,18802,29502,18632,24202,12792,18572],"class_list":["post-218762","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-society-culture","tag-big-data-2017","tag-data-science","tag-department-of-computer-science","tag-featured-post-side","tag-hajim-school-of-engineering-and-applied-sciences","tag-jiebo-luo","tag-politics","tag-research-finding"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Twitter researchers offer clues for why Trump won<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Twitter researchers offer clues for why Trump won\" \/>\n<meta property=\"og:description\" content=\"The more Donald Trump tweeted, the faster his following grew, even after he sparked controversies. This is among the many findings from an exhaustive 14-month study of each candidate&#039;s tweets during the 2016 election by researchers Jiebo Luo and Yu Wang.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/\" \/>\n<meta property=\"og:site_name\" content=\"News Center\" \/>\n<meta property=\"article:published_time\" content=\"2017-02-20T21:22:58+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-10-29T19:15:02+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/fea-trump-tweet-1.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"600\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Bob Marcotte\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Bob Marcotte\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/\"},\"author\":{\"name\":\"Bob Marcotte\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#\\\/schema\\\/person\\\/e0d8d271cd290d592461fa9cefca013b\"},\"headline\":\"Twitter researchers offer clues for why Trump won\",\"datePublished\":\"2017-02-20T21:22:58+00:00\",\"dateModified\":\"2024-10-29T19:15:02+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/\"},\"wordCount\":1022,\"image\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2017\\\/02\\\/fea-trump-tweet-1.jpg\",\"keywords\":[\"big-data-2017\",\"data science\",\"Department of Computer Science\",\"featured-post-side\",\"Hajim School of Engineering and Applied Sciences\",\"Jiebo Luo\",\"politics\",\"research finding\"],\"articleSection\":[\"Society &amp; Culture\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/\",\"name\":\"Twitter researchers offer clues for why Trump won\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2017\\\/02\\\/fea-trump-tweet-1.jpg\",\"datePublished\":\"2017-02-20T21:22:58+00:00\",\"dateModified\":\"2024-10-29T19:15:02+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#\\\/schema\\\/person\\\/e0d8d271cd290d592461fa9cefca013b\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2017\\\/02\\\/fea-trump-tweet-1.jpg\",\"contentUrl\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/wp-content\\\/uploads\\\/2017\\\/02\\\/fea-trump-tweet-1.jpg\",\"width\":1000,\"height\":600,\"caption\":\"man in crowd holds sign edited to read MAKE AMERICA TWEET AGAIN\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Twitter researchers offer clues for why Trump won\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#website\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/\",\"name\":\"News Center\",\"description\":\"Ä¢¹½´«Ã½\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/#\\\/schema\\\/person\\\/e0d8d271cd290d592461fa9cefca013b\",\"name\":\"Bob Marcotte\",\"url\":\"https:\\\/\\\/www.rochester.edu\\\/newscenter\\\/author\\\/bmarcotte\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Twitter researchers offer clues for why Trump won","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/","og_locale":"en_US","og_type":"article","og_title":"Twitter researchers offer clues for why Trump won","og_description":"The more Donald Trump tweeted, the faster his following grew, even after he sparked controversies. This is among the many findings from an exhaustive 14-month study of each candidate's tweets during the 2016 election by researchers Jiebo Luo and Yu Wang.","og_url":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/","og_site_name":"News Center","article_published_time":"2017-02-20T21:22:58+00:00","article_modified_time":"2024-10-29T19:15:02+00:00","og_image":[{"url":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/fea-trump-tweet-1.jpg","width":1000,"height":600,"type":"image\/jpeg"}],"author":"Bob Marcotte","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Bob Marcotte","Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/#article","isPartOf":{"@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/"},"author":{"name":"Bob Marcotte","@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/e0d8d271cd290d592461fa9cefca013b"},"headline":"Twitter researchers offer clues for why Trump won","datePublished":"2017-02-20T21:22:58+00:00","dateModified":"2024-10-29T19:15:02+00:00","mainEntityOfPage":{"@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/"},"wordCount":1022,"image":{"@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/#primaryimage"},"thumbnailUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/fea-trump-tweet-1.jpg","keywords":["big-data-2017","data science","Department of Computer Science","featured-post-side","Hajim School of Engineering and Applied Sciences","Jiebo Luo","politics","research finding"],"articleSection":["Society &amp; Culture"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/","url":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/","name":"Twitter researchers offer clues for why Trump won","isPartOf":{"@id":"https:\/\/www.rochester.edu\/newscenter\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/#primaryimage"},"image":{"@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/#primaryimage"},"thumbnailUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/fea-trump-tweet-1.jpg","datePublished":"2017-02-20T21:22:58+00:00","dateModified":"2024-10-29T19:15:02+00:00","author":{"@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/e0d8d271cd290d592461fa9cefca013b"},"breadcrumb":{"@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/#primaryimage","url":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/fea-trump-tweet-1.jpg","contentUrl":"https:\/\/www.rochester.edu\/newscenter\/wp-content\/uploads\/2017\/02\/fea-trump-tweet-1.jpg","width":1000,"height":600,"caption":"man in crowd holds sign edited to read MAKE AMERICA TWEET AGAIN"},{"@type":"BreadcrumbList","@id":"https:\/\/www.rochester.edu\/newscenter\/what-twitter-and-data-science-tell-us-about-the-2016-election-218762\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.rochester.edu\/newscenter\/"},{"@type":"ListItem","position":2,"name":"Twitter researchers offer clues for why Trump won"}]},{"@type":"WebSite","@id":"https:\/\/www.rochester.edu\/newscenter\/#website","url":"https:\/\/www.rochester.edu\/newscenter\/","name":"News Center","description":"Ä¢¹½´«Ã½","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.rochester.edu\/newscenter\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.rochester.edu\/newscenter\/#\/schema\/person\/e0d8d271cd290d592461fa9cefca013b","name":"Bob Marcotte","url":"https:\/\/www.rochester.edu\/newscenter\/author\/bmarcotte\/"}]}},"_links":{"self":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/218762","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/users\/286"}],"replies":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/comments?post=218762"}],"version-history":[{"count":34,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/218762\/revisions"}],"predecessor-version":[{"id":626052,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/posts\/218762\/revisions\/626052"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/media\/220192"}],"wp:attachment":[{"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/media?parent=218762"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/categories?post=218762"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.rochester.edu\/newscenter\/wp-json\/wp\/v2\/tags?post=218762"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}