CINXE.COM

<!DOCTYPE html> <html lang="en-US"> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <meta name='robots' content='index, follow, max-image-preview:large, max-snippet:-1, max-video-preview:-1' /> <style>img:is([sizes="auto" i], [sizes^="auto," i]) { contain-intrinsic-size: 3000px 1500px }</style>  <title>Detecting Risk and Protective Factors of Mental Health using Social Media Linked with Electronic Health Records - Center for Language and Speech Processing</title> <link rel="canonical" href="https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/" /> <meta property="og:locale" content="en_US" /> <meta property="og:type" content="article" /> <meta property="og:title" content="Detecting Risk and Protective Factors of Mental Health using Social Media Linked with Electronic Health Records - Center for Language and Speech Processing" /> <meta property="og:description" content="Research Group of the 2016 Third Frederick Jelinek Memorial Summer Workshop Team Presentations and Publications Introduction We propose a workshop centered around the first-of-its-kind “Penn SoMe+EHR Bank” [18], consisting of the electronic health records (EHR) and social media (SoMe) posts of thousands of consenting ER patients in the Philadelphia health system. We will focus on […]" /> <meta property="og:url" content="https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/" /> <meta property="og:site_name" content="Center for Language and Speech Processing" /> <meta property="article:modified_time" content="2018-05-15T20:33:59+00:00" /> <meta property="og:image" content="https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk-1024x682.jpg" /> <meta name="twitter:label1" content="Est. reading time" /> <meta name="twitter:data1" content="7 minutes" /> <meta name="twitter:label2" content="Written by" /> <meta name="twitter:data2" content="pkoehn1" /> <script type="application/ld+json" class="yoast-schema-graph">{"@context":"https://schema.org","@graph":[{"@type":"WebPage","@id":"https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/","url":"https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/","name":"Detecting Risk and Protective Factors of Mental Health using Social Media Linked with Electronic Health Records - Center for Language and Speech Processing","isPartOf":{"@id":"https://www.clsp.jhu.edu/#website"},"primaryImageOfPage":{"@id":"https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/#primaryimage"},"image":{"@id":"https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/#primaryimage"},"thumbnailUrl":"https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk-1024x682.jpg","datePublished":"2016-01-29T20:57:09+00:00","dateModified":"2018-05-15T20:33:59+00:00","breadcrumb":{"@id":"https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/#primaryimage","url":"https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk.jpg","contentUrl":"https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk.jpg","width":1200,"height":799,"caption":"\"Detecting Risk and Protective Factors of Mental Health using Social Media Linked with Electronic Health Records\" research group"},{"@type":"BreadcrumbList","@id":"https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://www.clsp.jhu.edu/"},{"@type":"ListItem","position":2,"name":"Workshops","item":"https://www.clsp.jhu.edu/workshops/"},{"@type":"ListItem","position":3,"name":"Third Frederick Jelinek Memorial Summer Workshop","item":"https://www.clsp.jhu.edu/workshops/16-workshop/"},{"@type":"ListItem","position":4,"name":"Detecting Risk and Protective Factors of Mental Health using Social Media Linked with Electronic Health Records"}]},{"@type":"WebSite","@id":"https://www.clsp.jhu.edu/#website","url":"https://www.clsp.jhu.edu/","name":"Center for Language and Speech Processing","description":"Johns Hopkins University","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://www.clsp.jhu.edu/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}</script>      <script type="text/javascript"> /* <![CDATA[ */ window._wpemojiSettings = {"baseUrl":"https:\/\/s.w.org\/images\/core\/emoji\/15.0.3\/72x72\/","ext":".png","svgUrl":"https:\/\/s.w.org\/images\/core\/emoji\/15.0.3\/svg\/","svgExt":".svg","source":{"concatemoji":"https:\/\/www.clsp.jhu.edu\/wp-includes\/js\/wp-emoji-release.min.js?ver=0db417805d51931f0f17316a3e6b0de3"}}; /*! This file is auto-generated */ !function(i,n){var o,s,e;function c(e){try{var t={supportTests:e,timestamp:(new Date).valueOf()};sessionStorage.setItem(o,JSON.stringify(t))}catch(e){}}function p(e,t,n){e.clearRect(0,0,e.canvas.width,e.canvas.height),e.fillText(t,0,0);var t=new Uint32Array(e.getImageData(0,0,e.canvas.width,e.canvas.height).data),r=(e.clearRect(0,0,e.canvas.width,e.canvas.height),e.fillText(n,0,0),new Uint32Array(e.getImageData(0,0,e.canvas.width,e.canvas.height).data));return t.every(function(e,t){return e===r[t]})}function u(e,t,n){switch(t){case"flag":return n(e,"\ud83c\udff3\ufe0f\u200d\u26a7\ufe0f","\ud83c\udff3\ufe0f\u200b\u26a7\ufe0f")?!1:!n(e,"\ud83c\uddfa\ud83c\uddf3","\ud83c\uddfa\u200b\ud83c\uddf3")&&!n(e,"\ud83c\udff4\udb40\udc67\udb40\udc62\udb40\udc65\udb40\udc6e\udb40\udc67\udb40\udc7f","\ud83c\udff4\u200b\udb40\udc67\u200b\udb40\udc62\u200b\udb40\udc65\u200b\udb40\udc6e\u200b\udb40\udc67\u200b\udb40\udc7f");case"emoji":return!n(e,"\ud83d\udc26\u200d\u2b1b","\ud83d\udc26\u200b\u2b1b")}return!1}function f(e,t,n){var r="undefined"!=typeof WorkerGlobalScope&&self instanceof WorkerGlobalScope?new OffscreenCanvas(300,150):i.createElement("canvas"),a=r.getContext("2d",{willReadFrequently:!0}),o=(a.textBaseline="top",a.font="600 32px Arial",{});return e.forEach(function(e){o[e]=t(a,e,n)}),o}function t(e){var t=i.createElement("script");t.src=e,t.defer=!0,i.head.appendChild(t)}"undefined"!=typeof Promise&&(o="wpEmojiSettingsSupports",s=["flag","emoji"],n.supports={everything:!0,everythingExceptFlag:!0},e=new Promise(function(e){i.addEventListener("DOMContentLoaded",e,{once:!0})}),new Promise(function(t){var n=function(){try{var e=JSON.parse(sessionStorage.getItem(o));if("object"==typeof e&&"number"==typeof e.timestamp&&(new Date).valueOf()<e.timestamp+604800&&"object"==typeof e.supportTests)return e.supportTests}catch(e){}return null}();if(!n){if("undefined"!=typeof Worker&&"undefined"!=typeof OffscreenCanvas&&"undefined"!=typeof URL&&URL.createObjectURL&&"undefined"!=typeof Blob)try{var e="postMessage("+f.toString()+"("+[JSON.stringify(s),u.toString(),p.toString()].join(",")+"));",r=new Blob([e],{type:"text/javascript"}),a=new Worker(URL.createObjectURL(r),{name:"wpTestEmojiSupports"});return void(a.onmessage=function(e){c(n=e.data),a.terminate(),t(n)})}catch(e){}c(n=f(s,u,p))}t(n)}).then(function(e){for(var t in e)n.supports[t]=e[t],n.supports.everything=n.supports.everything&&n.supports[t],"flag"!==t&&(n.supports.everythingExceptFlag=n.supports.everythingExceptFlag&&n.supports[t]);n.supports.everythingExceptFlag=n.supports.everythingExceptFlag&&!n.supports.flag,n.DOMReady=!1,n.readyCallback=function(){n.DOMReady=!0}}).then(function(){return e}).then(function(){var e;n.supports.everything||(n.readyCallback(),(e=n.source||{}).concatemoji?t(e.concatemoji):e.wpemoji&&e.twemoji&&(t(e.twemoji),t(e.wpemoji)))}))}((window,document),window._wpemojiSettings); /* ]]> */ </script> <link rel='stylesheet' id='wgs2-css' href='https://www.clsp.jhu.edu/wp-content/plugins/wp-google-search/wgs2.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='ai1ec_style-css' href='//www.clsp.jhu.edu/wp-content/plugins/all-in-one-event-calendar/cache/5f8aa77d_ai1ec_parsed_css.css?ver=3.0.0' type='text/css' media='all' /> <link rel='stylesheet' id='embed-pdf-viewer-css' href='https://www.clsp.jhu.edu/wp-content/plugins/embed-pdf-viewer/css/embed-pdf-viewer.css?ver=2.4.6' type='text/css' media='screen' /> <link rel='stylesheet' id='papercite_css-css' href='https://www.clsp.jhu.edu/wp-content/plugins/papercite/papercite.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <style id='wp-emoji-styles-inline-css' type='text/css'> img.wp-smiley, img.emoji { display: inline !important; border: none !important; box-shadow: none !important; height: 1em !important; width: 1em !important; margin: 0 0.07em !important; vertical-align: -0.1em !important; background: none !important; padding: 0 !important; } </style> <link rel='stylesheet' id='wp-block-library-css' href='https://www.clsp.jhu.edu/wp-includes/css/dist/block-library/style.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='wp-components-css' href='https://www.clsp.jhu.edu/wp-includes/css/dist/components/style.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='wp-preferences-css' href='https://www.clsp.jhu.edu/wp-includes/css/dist/preferences/style.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='wp-block-editor-css' href='https://www.clsp.jhu.edu/wp-includes/css/dist/block-editor/style.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='wp-reusable-blocks-css' href='https://www.clsp.jhu.edu/wp-includes/css/dist/reusable-blocks/style.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='wp-patterns-css' href='https://www.clsp.jhu.edu/wp-includes/css/dist/patterns/style.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='wp-editor-css' href='https://www.clsp.jhu.edu/wp-includes/css/dist/editor/style.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='algori_pdf_viewer-cgb-style-css-css' href='https://www.clsp.jhu.edu/wp-content/plugins/algori-pdf-viewer/dist/blocks.style.build.css' type='text/css' media='all' /> <style id='co-authors-plus-coauthors-style-inline-css' type='text/css'> .wp-block-co-authors-plus-coauthors.is-layout-flow [class*=wp-block-co-authors-plus]{display:inline} </style> <style id='co-authors-plus-avatar-style-inline-css' type='text/css'> .wp-block-co-authors-plus-avatar :where(img){height:auto;max-width:100%;vertical-align:bottom}.wp-block-co-authors-plus-coauthors.is-layout-flow .wp-block-co-authors-plus-avatar :where(img){vertical-align:middle}.wp-block-co-authors-plus-avatar:is(.alignleft,.alignright){display:table}.wp-block-co-authors-plus-avatar.aligncenter{display:table;margin-inline:auto} </style> <style id='co-authors-plus-image-style-inline-css' type='text/css'> .wp-block-co-authors-plus-image{margin-bottom:0}.wp-block-co-authors-plus-image :where(img){height:auto;max-width:100%;vertical-align:bottom}.wp-block-co-authors-plus-coauthors.is-layout-flow .wp-block-co-authors-plus-image :where(img){vertical-align:middle}.wp-block-co-authors-plus-image:is(.alignfull,.alignwide) :where(img){width:100%}.wp-block-co-authors-plus-image:is(.alignleft,.alignright){display:table}.wp-block-co-authors-plus-image.aligncenter{display:table;margin-inline:auto} </style> <style id='tropicalista-pdfembed-style-inline-css' type='text/css'> .wp-block-tropicalista-pdfembed{height:500px;min-height:500px} </style> <style id='classic-theme-styles-inline-css' type='text/css'> /*! This file is auto-generated */ .wp-block-button__link{color:#fff;background-color:#32373c;border-radius:9999px;box-shadow:none;text-decoration:none;padding:calc(.667em + 2px) calc(1.333em + 2px);font-size:1.125em}.wp-block-file__button{background:#32373c;color:#fff;text-decoration:none} </style> <style id='global-styles-inline-css' type='text/css'> :root{--wp--preset--aspect-ratio--square: 1;--wp--preset--aspect-ratio--4-3: 4/3;--wp--preset--aspect-ratio--3-4: 3/4;--wp--preset--aspect-ratio--3-2: 3/2;--wp--preset--aspect-ratio--2-3: 2/3;--wp--preset--aspect-ratio--16-9: 16/9;--wp--preset--aspect-ratio--9-16: 9/16;--wp--preset--color--black: #000000;--wp--preset--color--cyan-bluish-gray: #abb8c3;--wp--preset--color--white: #ffffff;--wp--preset--color--pale-pink: #f78da7;--wp--preset--color--vivid-red: #cf2e2e;--wp--preset--color--luminous-vivid-orange: #ff6900;--wp--preset--color--luminous-vivid-amber: #fcb900;--wp--preset--color--light-green-cyan: #7bdcb5;--wp--preset--color--vivid-green-cyan: #00d084;--wp--preset--color--pale-cyan-blue: #8ed1fc;--wp--preset--color--vivid-cyan-blue: #0693e3;--wp--preset--color--vivid-purple: #9b51e0;--wp--preset--gradient--vivid-cyan-blue-to-vivid-purple: linear-gradient(135deg,rgba(6,147,227,1) 0%,rgb(155,81,224) 100%);--wp--preset--gradient--light-green-cyan-to-vivid-green-cyan: linear-gradient(135deg,rgb(122,220,180) 0%,rgb(0,208,130) 100%);--wp--preset--gradient--luminous-vivid-amber-to-luminous-vivid-orange: linear-gradient(135deg,rgba(252,185,0,1) 0%,rgba(255,105,0,1) 100%);--wp--preset--gradient--luminous-vivid-orange-to-vivid-red: linear-gradient(135deg,rgba(255,105,0,1) 0%,rgb(207,46,46) 100%);--wp--preset--gradient--very-light-gray-to-cyan-bluish-gray: linear-gradient(135deg,rgb(238,238,238) 0%,rgb(169,184,195) 100%);--wp--preset--gradient--cool-to-warm-spectrum: linear-gradient(135deg,rgb(74,234,220) 0%,rgb(151,120,209) 20%,rgb(207,42,186) 40%,rgb(238,44,130) 60%,rgb(251,105,98) 80%,rgb(254,248,76) 100%);--wp--preset--gradient--blush-light-purple: linear-gradient(135deg,rgb(255,206,236) 0%,rgb(152,150,240) 100%);--wp--preset--gradient--blush-bordeaux: linear-gradient(135deg,rgb(254,205,165) 0%,rgb(254,45,45) 50%,rgb(107,0,62) 100%);--wp--preset--gradient--luminous-dusk: linear-gradient(135deg,rgb(255,203,112) 0%,rgb(199,81,192) 50%,rgb(65,88,208) 100%);--wp--preset--gradient--pale-ocean: linear-gradient(135deg,rgb(255,245,203) 0%,rgb(182,227,212) 50%,rgb(51,167,181) 100%);--wp--preset--gradient--electric-grass: linear-gradient(135deg,rgb(202,248,128) 0%,rgb(113,206,126) 100%);--wp--preset--gradient--midnight: linear-gradient(135deg,rgb(2,3,129) 0%,rgb(40,116,252) 100%);--wp--preset--font-size--small: 13px;--wp--preset--font-size--medium: 20px;--wp--preset--font-size--large: 36px;--wp--preset--font-size--x-large: 42px;--wp--preset--spacing--20: 0.44rem;--wp--preset--spacing--30: 0.67rem;--wp--preset--spacing--40: 1rem;--wp--preset--spacing--50: 1.5rem;--wp--preset--spacing--60: 2.25rem;--wp--preset--spacing--70: 3.38rem;--wp--preset--spacing--80: 5.06rem;--wp--preset--shadow--natural: 6px 6px 9px rgba(0, 0, 0, 0.2);--wp--preset--shadow--deep: 12px 12px 50px rgba(0, 0, 0, 0.4);--wp--preset--shadow--sharp: 6px 6px 0px rgba(0, 0, 0, 0.2);--wp--preset--shadow--outlined: 6px 6px 0px -3px rgba(255, 255, 255, 1), 6px 6px rgba(0, 0, 0, 1);--wp--preset--shadow--crisp: 6px 6px 0px rgba(0, 0, 0, 1);}:where(.is-layout-flex){gap: 0.5em;}:where(.is-layout-grid){gap: 0.5em;}body .is-layout-flex{display: flex;}.is-layout-flex{flex-wrap: wrap;align-items: center;}.is-layout-flex > :is(*, div){margin: 0;}body .is-layout-grid{display: grid;}.is-layout-grid > :is(*, div){margin: 0;}:where(.wp-block-columns.is-layout-flex){gap: 2em;}:where(.wp-block-columns.is-layout-grid){gap: 2em;}:where(.wp-block-post-template.is-layout-flex){gap: 1.25em;}:where(.wp-block-post-template.is-layout-grid){gap: 1.25em;}.has-black-color{color: var(--wp--preset--color--black) !important;}.has-cyan-bluish-gray-color{color: var(--wp--preset--color--cyan-bluish-gray) !important;}.has-white-color{color: var(--wp--preset--color--white) !important;}.has-pale-pink-color{color: var(--wp--preset--color--pale-pink) !important;}.has-vivid-red-color{color: var(--wp--preset--color--vivid-red) !important;}.has-luminous-vivid-orange-color{color: var(--wp--preset--color--luminous-vivid-orange) !important;}.has-luminous-vivid-amber-color{color: var(--wp--preset--color--luminous-vivid-amber) !important;}.has-light-green-cyan-color{color: var(--wp--preset--color--light-green-cyan) !important;}.has-vivid-green-cyan-color{color: var(--wp--preset--color--vivid-green-cyan) !important;}.has-pale-cyan-blue-color{color: var(--wp--preset--color--pale-cyan-blue) !important;}.has-vivid-cyan-blue-color{color: var(--wp--preset--color--vivid-cyan-blue) !important;}.has-vivid-purple-color{color: var(--wp--preset--color--vivid-purple) !important;}.has-black-background-color{background-color: var(--wp--preset--color--black) !important;}.has-cyan-bluish-gray-background-color{background-color: var(--wp--preset--color--cyan-bluish-gray) !important;}.has-white-background-color{background-color: var(--wp--preset--color--white) !important;}.has-pale-pink-background-color{background-color: var(--wp--preset--color--pale-pink) !important;}.has-vivid-red-background-color{background-color: var(--wp--preset--color--vivid-red) !important;}.has-luminous-vivid-orange-background-color{background-color: var(--wp--preset--color--luminous-vivid-orange) !important;}.has-luminous-vivid-amber-background-color{background-color: var(--wp--preset--color--luminous-vivid-amber) !important;}.has-light-green-cyan-background-color{background-color: var(--wp--preset--color--light-green-cyan) !important;}.has-vivid-green-cyan-background-color{background-color: var(--wp--preset--color--vivid-green-cyan) !important;}.has-pale-cyan-blue-background-color{background-color: var(--wp--preset--color--pale-cyan-blue) !important;}.has-vivid-cyan-blue-background-color{background-color: var(--wp--preset--color--vivid-cyan-blue) !important;}.has-vivid-purple-background-color{background-color: var(--wp--preset--color--vivid-purple) !important;}.has-black-border-color{border-color: var(--wp--preset--color--black) !important;}.has-cyan-bluish-gray-border-color{border-color: var(--wp--preset--color--cyan-bluish-gray) !important;}.has-white-border-color{border-color: var(--wp--preset--color--white) !important;}.has-pale-pink-border-color{border-color: var(--wp--preset--color--pale-pink) !important;}.has-vivid-red-border-color{border-color: var(--wp--preset--color--vivid-red) !important;}.has-luminous-vivid-orange-border-color{border-color: var(--wp--preset--color--luminous-vivid-orange) !important;}.has-luminous-vivid-amber-border-color{border-color: var(--wp--preset--color--luminous-vivid-amber) !important;}.has-light-green-cyan-border-color{border-color: var(--wp--preset--color--light-green-cyan) !important;}.has-vivid-green-cyan-border-color{border-color: var(--wp--preset--color--vivid-green-cyan) !important;}.has-pale-cyan-blue-border-color{border-color: var(--wp--preset--color--pale-cyan-blue) !important;}.has-vivid-cyan-blue-border-color{border-color: var(--wp--preset--color--vivid-cyan-blue) !important;}.has-vivid-purple-border-color{border-color: var(--wp--preset--color--vivid-purple) !important;}.has-vivid-cyan-blue-to-vivid-purple-gradient-background{background: var(--wp--preset--gradient--vivid-cyan-blue-to-vivid-purple) !important;}.has-light-green-cyan-to-vivid-green-cyan-gradient-background{background: var(--wp--preset--gradient--light-green-cyan-to-vivid-green-cyan) !important;}.has-luminous-vivid-amber-to-luminous-vivid-orange-gradient-background{background: var(--wp--preset--gradient--luminous-vivid-amber-to-luminous-vivid-orange) !important;}.has-luminous-vivid-orange-to-vivid-red-gradient-background{background: var(--wp--preset--gradient--luminous-vivid-orange-to-vivid-red) !important;}.has-very-light-gray-to-cyan-bluish-gray-gradient-background{background: var(--wp--preset--gradient--very-light-gray-to-cyan-bluish-gray) !important;}.has-cool-to-warm-spectrum-gradient-background{background: var(--wp--preset--gradient--cool-to-warm-spectrum) !important;}.has-blush-light-purple-gradient-background{background: var(--wp--preset--gradient--blush-light-purple) !important;}.has-blush-bordeaux-gradient-background{background: var(--wp--preset--gradient--blush-bordeaux) !important;}.has-luminous-dusk-gradient-background{background: var(--wp--preset--gradient--luminous-dusk) !important;}.has-pale-ocean-gradient-background{background: var(--wp--preset--gradient--pale-ocean) !important;}.has-electric-grass-gradient-background{background: var(--wp--preset--gradient--electric-grass) !important;}.has-midnight-gradient-background{background: var(--wp--preset--gradient--midnight) !important;}.has-small-font-size{font-size: var(--wp--preset--font-size--small) !important;}.has-medium-font-size{font-size: var(--wp--preset--font-size--medium) !important;}.has-large-font-size{font-size: var(--wp--preset--font-size--large) !important;}.has-x-large-font-size{font-size: var(--wp--preset--font-size--x-large) !important;} :where(.wp-block-post-template.is-layout-flex){gap: 1.25em;}:where(.wp-block-post-template.is-layout-grid){gap: 1.25em;} :where(.wp-block-columns.is-layout-flex){gap: 2em;}:where(.wp-block-columns.is-layout-grid){gap: 2em;} :root :where(.wp-block-pullquote){font-size: 1.5em;line-height: 1.6;} </style> <link rel='stylesheet' id='embedpress-style-css' href='https://www.clsp.jhu.edu/wp-content/plugins/embedpress/assets/css/embedpress.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='dashicons-css' href='https://www.clsp.jhu.edu/wp-includes/css/dashicons.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='video-js-css' href='https://www.clsp.jhu.edu/wp-content/plugins/video-embed-thumbnail-generator/video-js/video-js.min.css?ver=7.11.4' type='text/css' media='all' /> <link rel='stylesheet' id='video-js-kg-skin-css' href='https://www.clsp.jhu.edu/wp-content/plugins/video-embed-thumbnail-generator/video-js/kg-video-js-skin.css?ver=4.10.2' type='text/css' media='all' /> <link rel='stylesheet' id='kgvid_video_styles-css' href='https://www.clsp.jhu.edu/wp-content/plugins/video-embed-thumbnail-generator/src/public/css/videopack-styles.css?ver=4.10.2' type='text/css' media='all' /> <link rel='stylesheet' id='wse-centers-frontend-css' href='https://www.clsp.jhu.edu/wp-content/uploads/wp-less/wse-clsp/assets/stylesheets/front-fd62ec785a.css' type='text/css' media='all' /> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-includes/js/jquery/jquery.min.js?ver=3.7.1" id="jquery-core-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-includes/js/jquery/jquery-migrate.min.js?ver=3.4.1" id="jquery-migrate-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/plugins/papercite/js/papercite.js?ver=0db417805d51931f0f17316a3e6b0de3" id="papercite-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/themes/wse/assets/javascripts/modernizr.js?ver=0db417805d51931f0f17316a3e6b0de3" id="theme-modernizr-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/themes/wse/assets/javascripts/jquery.cookie.js?ver=0db417805d51931f0f17316a3e6b0de3" id="theme-cookie-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/themes/wse/vendor/twitter/bootstrap/docs/assets/js/bootstrap.min.js?ver=0db417805d51931f0f17316a3e6b0de3" id="theme-bootstrap-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/themes/wse/assets/javascripts/rotator.js?ver=0db417805d51931f0f17316a3e6b0de3" id="theme-rotator-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/themes/wse/assets/javascripts/jquery.scrollto.min.js?ver=0db417805d51931f0f17316a3e6b0de3" id="theme-scrollto-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/themes/wse/assets/javascripts/jquery.breakpoints.js?ver=0db417805d51931f0f17316a3e6b0de3" id="theme-breakpoints-js"></script> <script type="text/javascript" id="theme-site-js-extra"> /* <![CDATA[ */ var theme_vars = {"home_url":"https:\/\/www.clsp.jhu.edu","network_home_url":"https:\/\/www.clsp.jhu.edu","ajaxurl":"https:\/\/www.clsp.jhu.edu\/wp-admin\/admin-ajax.php","department_site":"1"}; /* ]]> */ </script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/themes/wse/assets/javascripts/site.js?ver=1.0.1" id="theme-site-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/themes/wse/assets/javascripts/jquery.placeholder.min.js?ver=0db417805d51931f0f17316a3e6b0de3" id="theme-placeholders-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/themes/wse-clsp/assets/javascripts/site.js?ver=0db417805d51931f0f17316a3e6b0de3" id="center-site-js"></script> <link rel="https://api.w.org/" href="https://www.clsp.jhu.edu/wp-json/" /><link rel="alternate" title="JSON" type="application/json" href="https://www.clsp.jhu.edu/wp-json/wp/v2/pages/9601" /><link rel="EditURI" type="application/rsd+xml" title="RSD" href="https://www.clsp.jhu.edu/xmlrpc.php?rsd" /> <link rel='shortlink' href='https://www.clsp.jhu.edu/?p=9601' /> <link rel="alternate" title="oEmbed (JSON)" type="application/json+oembed" href="https://www.clsp.jhu.edu/wp-json/oembed/1.0/embed?url=https%3A%2F%2Fwww.clsp.jhu.edu%2Fworkshops%2F16-workshop%2Fdetecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records%2F" /> <link rel="alternate" title="oEmbed (XML)" type="text/xml+oembed" href="https://www.clsp.jhu.edu/wp-json/oembed/1.0/embed?url=https%3A%2F%2Fwww.clsp.jhu.edu%2Fworkshops%2F16-workshop%2Fdetecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records%2F&format=xml" />  <style type="text/css"> .page-header .site-title img { width: 250px; } .page-header .wse-logo { float: left; } .page-header .site-title { float: right; }</style>   <style type="text/css"> .gsc-search-box-tools .gsc-search-box { padding-left: 12px !important; padding-right: 12px !important; } .gsc-input-box { border: solid !important; border-width: 1px !important; } form.gsc-search-box { width: 240px !important; } input#gsc-i-id1.gsc-input { background: none !important; } .sidebar-header-right { overflow: hidden; } .gsc-search-button-v2 { border-color: #902d2f !important; background-color: #902d2f !important; } .gsc-search-button-v2:hover { border-color: #902d2f !important; background-color: #902d2f !important; }</style>   <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/plugins/teachpress/js/frontend.js?ver=9.0.6"></script> <link type="text/css" href="https://www.clsp.jhu.edu/wp-content/plugins/teachpress/styles/teachpress_front.css?ver=9.0.6" rel="stylesheet" />   </head> <body class="page-template-default page page-id-9601 page-parent page-child parent-pageid-9569 header-title-font-serif wse-department nav-base" itemscope itemtype="http://schema.org/WebPage"> <div class="content-wrap"> <div class="page-wrap-container"> <div class="page-wrap"> <header class="page-header"> <div class="container"> <div class="title"> <div class="wse-logo-container"> <div class="wse-logo"> <a href="https://engineering.jhu.edu"> <img src="https://www.clsp.jhu.edu/wp-content/themes/wse-clsp/assets/images/wse-logo-blue@2x.png" /> </a> </div> </div> <div class="site-title-container"> <h1 class="site-title "> <a href="https://www.clsp.jhu.edu"> <span class="image-container" style="max-width: 200px;"> <img src="https://www.clsp.jhu.edu/wp-content/uploads/2016/07/Modified-CLSP-Logo-with-Vertical-Text-e1460641018761-300x123.png" alt="Center for Language and Speech Processing" /> </span> </a> </h1> </div> </div> </div> <div class="visible-phone responsive-menu-trigger-container"> <a class="visible-phone responsive-menu-trigger" data-toggle="phone-menu" href="#"> <span class="menu-bars"> <span class="bar"></span> <span class="bar"></span> <span class="bar last-bar"></span> </span> </a> </div> <nav id="main-nav" class="base font-normal"> <div class="container"> <div class="sidebar-header-right"> <div id="wgs_widget-2" class="widget widget_wgs_widget"><div class="wgs_wrapper"><div class="gcse-searchbox-only" data-resultsUrl="https://www.clsp.jhu.edu/search_gcse/"></div></div></div> </div> <div class="menu-primary-menu-container"><ul id="menu-primary-menu" class="menu"><li id="menu-item-8746" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-home menu-item-8746"><a href="https://www.clsp.jhu.edu/">Home</a></li> <li id="menu-item-4116" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-has-children menu-item-4116"><a href="https://www.clsp.jhu.edu/about/">About</a> <ul class="sub-menu"> <li id="menu-item-18654" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-18654"><a href="https://www.clsp.jhu.edu/about/diversity-and-inclusion/">Diversity and Inclusion</a></li> <li id="menu-item-19580" class="menu-item menu-item-type-custom menu-item-object-custom menu-item-19580 has-icon "><a href="https://covidinfo.jhu.edu/health-safety/"><span class="fontawesome-text">Health + Safety: Coronavirus Information</span> <i class="icon-external"> </i></a></li> <li id="menu-item-4146" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-4146"><a href="https://www.clsp.jhu.edu/contact/">Contact Us/Visit Us</a></li> <li id="menu-item-9666" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-9666"><a href="https://www.clsp.jhu.edu/workshops/internships/">Internships</a></li> <li id="menu-item-5835" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-5835"><a href="https://www.clsp.jhu.edu/courses/">Courses</a></li> <li id="menu-item-4144" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-4144"><a href="https://www.clsp.jhu.edu/apply-for-phd/">Apply for PhD</a></li> <li id="menu-item-11014" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-11014"><a href="https://www.clsp.jhu.edu/about/jelinek-fellowship/">Jelinek Fellowship</a></li> <li id="menu-item-4145" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-4145"><a href="https://www.clsp.jhu.edu/employment-opportunities/">Employment Opportunities</a></li> <li id="menu-item-23742" class="menu-item menu-item-type-custom menu-item-object-custom menu-item-23742 has-icon "><a href="https://secure.jhu.edu/form/eng"><span class="fontawesome-text">Make a Donation</span> <i class="icon-external"> </i></a></li> </ul> </li> <li id="menu-item-9366" class="menu-item menu-item-type-custom menu-item-object-custom menu-item-has-children menu-item-9366"><a href="https://www.clsp.jhu.edu/faculty">People</a> <ul class="sub-menu"> <li id="menu-item-3998" class="menu-item menu-item-type-custom menu-item-object-custom menu-item-has-children menu-item-3998"><a href="https://www.clsp.jhu.edu/faculty">Faculty</a> <ul class="sub-menu"> <li id="menu-item-4134" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-4134"><a href="https://www.clsp.jhu.edu/people/affiliated-faculty/">Affiliated Faculty</a></li> <li id="menu-item-4131" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-4131"><a href="https://www.clsp.jhu.edu/people/former-faculty/">Former Faculty</a></li> </ul> </li> <li id="menu-item-4132" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-has-children menu-item-4132"><a href="https://www.clsp.jhu.edu/people/postdocs/">Postdocs</a> <ul class="sub-menu"> <li id="menu-item-17465" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-17465"><a href="https://www.clsp.jhu.edu/people/postdocs/">Current Postdocs</a></li> <li id="menu-item-17460" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-17460"><a href="https://www.clsp.jhu.edu/former-postdocs-and-research-staff/">Former Postdocs</a></li> </ul> </li> <li id="menu-item-4130" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-4130"><a href="https://www.clsp.jhu.edu/people/graduate-students/">Graduate Students</a></li> <li id="menu-item-4129" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-4129"><a href="https://www.clsp.jhu.edu/people/staff/">Staff</a></li> <li id="menu-item-4133" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-4133"><a href="https://www.clsp.jhu.edu/people/alumni/">Alumni</a></li> </ul> </li> <li id="menu-item-4113" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-4113"><a href="https://www.clsp.jhu.edu/publications/">Publications</a></li> <li id="menu-item-7084" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-has-children menu-item-7084"><a href="https://www.clsp.jhu.edu/seminars/">Seminars</a> <ul class="sub-menu"> <li id="menu-item-9364" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-9364"><a href="https://www.clsp.jhu.edu/seminars/">Seminar Calendar</a></li> <li id="menu-item-9133" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-9133"><a href="https://www.clsp.jhu.edu/seminars/seminar-videos/">Seminar Videos</a></li> </ul> </li> <li id="menu-item-4111" class="menu-item menu-item-type-post_type menu-item-object-page current-page-ancestor menu-item-4111"><a href="https://www.clsp.jhu.edu/workshops/">Workshops</a></li> <li id="menu-item-15691" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-15691"><a href="https://www.clsp.jhu.edu/human-language-technology-masters/">HLT Masters</a></li> <li id="menu-item-17965" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-has-children menu-item-17965"><a href="https://www.clsp.jhu.edu/employee-self-service/">Resources</a> <ul class="sub-menu"> <li id="menu-item-19583" class="menu-item menu-item-type-custom menu-item-object-custom menu-item-19583 has-icon "><a href="https://covidinfo.jhu.edu/health-safety/"><span class="fontawesome-text">Health + Safety: Coronavirus Information</span> <i class="icon-external"> </i></a></li> <li id="menu-item-20347" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-20347"><a href="https://www.clsp.jhu.edu/student-activities-committees/">Student Activities Committees</a></li> <li id="menu-item-17968" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-17968"><a href="https://www.clsp.jhu.edu/employee-self-service/">Employee Self-Service</a></li> <li id="menu-item-21006" class="menu-item menu-item-type-post_type menu-item-object-page menu-item-21006"><a href="https://www.clsp.jhu.edu/code-and-data-resources/">Code and Data Resources</a></li> </ul> </li> </ul></div> </div> </nav> </header> <div class="bd"> <div class="container"> <div class="black-opaque-bar decorator"></div> <div class="breadcrumb-container"> </div><div class="grid-with-gutters"> <div class="row"> <div class="span8"> <h1 class="page-title"> Detecting Risk and Protective Factors of Mental Health using Social Media Linked with Electronic Health Records </h1> <div class="the-content"> <ul> <li><i>Research Group of the <a href="https://www.clsp.jhu.edu/workshops/16-workshop/">2016 Third Frederick Jelinek Memorial Summer Workshop</a></i></li> <li><a href="https://www.clsp.jhu.edu/workshops/16-workshop/detecting-risk-and-protective-factors-of-mental-health-using-social-media-linked-with-electronic-health-records/team-presentations-publications/">Team Presentations and Publications</a></li> </ul> <h6><a href="https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk.jpg"><img fetchpriority="high" decoding="async" class="size-large wp-image-10386 aligncenter" src="https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk-1024x682.jpg" alt="ws16-detectingrisk" width="1024" height="682" srcset="https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk-1024x682.jpg 1024w, https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk-300x200.jpg 300w, https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk-768x511.jpg 768w, https://www.clsp.jhu.edu/wp-content/uploads/2016/10/ws16.detectingrisk.jpg 1200w" sizes="(max-width: 1024px) 100vw, 1024px" /></a></h6> <h6>Introduction</h6> <p>We propose a workshop centered around the first-of-its-kind “Penn SoMe+EHR Bank” [18], consisting of the electronic health records (EHR) and social media (SoMe) posts of thousands of consenting ER patients in the Philadelphia health system. We will focus on longitudinal analysis of social media to understand how the language and online behavior reflects the patients’ mental health diagnoses and medications (from the EHR). Our goals are to automatically detect crisis points in a patient’s lifeline, to discover features indicative of onset and recovery of mental health disorders, and to test the validity of prior research using social media for mental health – in particular, anxiety, eating disorders, drug abuse, and suicidal ideation.</p> <p>Mental health is a global issue, and one where bringing technology to bear could have a real impact. Global mental health expenditure is estimated at $3.5 trillion [2]. Every year, 19% of Americans experience mental illness [27] and an estimated 4% have thoughts of suicide [1]. Traditional mental health data gives practitioners and scientists little insight into the everyday thoughts, feelings, and behaviors of patients (i.e., personalized health). Social media, now used regularly by over a billion people worldwide, gives us an unprecedented record of people’s daily lives in the form of Facebook status updates, Tweets, or Instagram messages. These unprompted “big data” are recorded in the moment and subject to different biases than traditional survey or laboratory data, thus opening the door for data-driven discovery of previously inaccessible, everyday factors and personalized interventions in mental health.</p> <p>The strength of such data is reflected in the recent explosion of work using social media to detect and characterize individuals with mental health disorders [4, 5, 6, 9, 12, 13, 17, 25, 26]. The patterns found in these analyses are quite face valid (e.g., see Figures 1 and 2), corroborating the clinical literature. However, despite this large upswing in interest to tackle mental health through social media, there have been no studies linking social media language patterns with substantial clinical data – data to support such studies was lacking until the Penn SoMe+EHR Bank.</p> <table align="center"> <tbody> <tr> <td> <p><div id="attachment_9699" style="width: 310px" class="wp-caption aligncenter"><a href="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig1.png" rel="attachment wp-att-9699"><img decoding="async" aria-describedby="caption-attachment-9699" class="size-medium wp-image-9699" src="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig1-300x198.png" alt="Figure 1: Words and phrases most predictive of self-reported diagnosis of PTSD on Twitter (as compared to age- and gender-matched control users). The color indexes relative frequency, from grey (rarely used) through blue (moderately used) to red (frequently used)." width="300" height="198" srcset="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig1-300x198.png 300w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig1-768x507.png 768w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig1.png 843w" sizes="(max-width: 300px) 100vw, 300px" /></a><p id="caption-attachment-9699" class="wp-caption-text">Figure 1: Words and phrases most predictive of self-reported diagnosis of PTSD on Twitter (as compared to age- and gender-matched control users). The color indexes relative frequency, from grey (rarely used) through blue (moderately used) to red (frequently used).</p></div></td> <td> <p><div id="attachment_9698" style="width: 310px" class="wp-caption aligncenter"><a href="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig2.png" rel="attachment wp-att-9698"><img decoding="async" aria-describedby="caption-attachment-9698" class="size-medium wp-image-9698" src="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig2-300x193.png" alt="Figure 2: Topics (clusters of semantically-related words) most predictive of self-reported diagnosis of depression on Twitter (as compared to age- and gender-matched control users). Size indicates prevalence of word within topic." width="300" height="193" srcset="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig2-300x193.png 300w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig2.png 593w" sizes="(max-width: 300px) 100vw, 300px" /></a><p id="caption-attachment-9698" class="wp-caption-text">Figure 2: Topics (clusters of semantically-related words) most predictive of self-reported diagnosis of depression on Twitter (as compared to age- and gender-matched control users). Size indicates prevalence of word within topic.</p></div></td> </tr> </tbody> </table> <h6>Research Questions</h6> <p>The proposed research aims specifically to address the following questions:</p> <ol> <li>Can we forecast mental health onset and recovery, as signaled in clinical records, based on social media features?</li> </ol> <ol start="2"> <li>What are the signals from everyday life, as manifest in social media language, that precipitate a shift in mental health?</li> </ol> <ol start="3"> <li>How do prescribed medicines affect the signals emanating from everyday life, and do changes in the language in social media correlate to the known side effects of medications?</li> </ol> <p> </p> <h6>Approach</h6> <p>We propose exploratory and predictive analyses of the joint temporal, linguistic, and medical information made available by the Penn SoMe+EHR Bank. We seek quantifiable and insightful signals related to mental health. We propose to focus on four mental health conditions: anxiety, eating disorders, drug abuse, and suicidality. These four conditions are quite prevalent with stated progression and relapse yet have previously been largely neglected in social media–based studies.</p> <p>The proposed approach will begin with basic analysis of <em>linguistic characteristics</em> of the entries in a user’s timeline (i.e., Facebook status update, tweet, or Instagram post) coupled with the user’s linked diagnoses and/or prescribed medication information. The linguistic analysis will include basic natural language processing techniques previously demonstrated to have relevance to mental health, including language models, topic models, and sentiment analysis [5, 6, 15, 26]. One of the challenges this approach will have to face is that traditional techniques in NLP, designed to model documents or language itself, have limitations when modeling the people behind the language: variable encodings may not be appropriate [11], distributions may change, and predictive models are not always interpretable for person-level insights [19, 24]. As needed, deeper semantic representations and deep learning techniques will be employed.</p> <p>Key to our study will be the use of <em>time series analysis</em> of the user’s social media timeline – including features beyond the language content, to include metadata such as the time and frequency of posting. We have repeatedly found when examining language related to mental health that there is significant information encoded in time, and so explicit joint and conditional analysis of linguistic and temporal information may yield new insight into mental health processes. Mental health symptoms and medication effects ebb and flow with time [21] and at many granularities (hourly, daily, weekly and seasonally) [8, 16, 23], but these clinically relevant signals are not readily accessible by traditional approaches to mental health. The Zipfian nature of language which yields very sparse terms and phrases makes common approaches to time series analysis [3, 10] non-trivial; we will explore Bayesian change point models [22] as well as forecasting models (such as ARIMA) [20]. Interestingly, temporal-linguistic structure is prevalent in a number of applied NLP domains, so progress here may yield gains beyond mental health as well.</p> <p>Finally, we will conduct exploratory analysis of the highly-predictive, temporally-sensitive linguistic and metadata features to discover potential <em>risk and protective factors</em> for mental health. It will certainly be the case that the variables required to present a full picture of an individual’s changing mental health status will not all be present in the data, and so the models must be able to account for latent variables as well as the observables. Additionally, while clinical data is often looked to as some “gold standard” for the health of a patient, it does have a significant amount of error and noise. Clinical agreement on diagnoses related to mental health is particularly challenging at κ < 0.6 [14]. This means that the labeled diagnoses are not perfectly reliable, and techniques for supervised learning from noisy labels must be incorporated. Care will be taken to avoid discovery of spurious relationships by leveraging the size of our data to correct for the multiple hypotheses tested during exploratory analyses.</p> <table align="center"> <tbody> <tr> <td> <p><div id="attachment_9711" style="width: 289px" class="wp-caption aligncenter"><a href="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig3.png" rel="attachment wp-att-9711"><img loading="lazy" decoding="async" aria-describedby="caption-attachment-9711" class="wp-image-9711 size-full" src="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig3.png" alt="Figure 3: Size of SoMe+EHR Bank as of November 2015; expected to increase approximately 166% by June 2016. The mean number of status updates per user is 834." width="279" height="195" /></a><p id="caption-attachment-9711" class="wp-caption-text">Figure 3: Size of SoMe+EHR Bank as of November 2015; expected to increase approximately 166% by June 2016. The mean number of status updates per user is 834.</p></div></td> <td> <p><div id="attachment_9712" style="width: 291px" class="wp-caption aligncenter"><a href="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig4.png" rel="attachment wp-att-9712"><img loading="lazy" decoding="async" aria-describedby="caption-attachment-9712" class="wp-image-9712 size-full" src="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig4.png" alt="Figure 4: Number of Twitter users and their tweets from 2009-2015 with self-stated diagnoses of the listed conditions. The mean number of tweets per user is 3,084." width="281" height="143" /></a><p id="caption-attachment-9712" class="wp-caption-text">Figure 4: Number of Twitter users and their tweets from 2009-2015 with self-stated diagnoses of the listed conditions. The mean number of tweets per user is 3,084.</p></div></td> </tr> </tbody> </table> <p>Throughout the workshop we will be in regular discussion with our clinical panel and subject matter experts (see Team, below) to ensure that the analyses are reasonable, interpretable, and – hopefully – have the potential to effect real change in the field of mental health.</p> <p> </p> <h6>Data and Feasibility</h6> <p>Data connecting linguistic signals to markers of mental illness, diagnoses, or outcomes, has been traditionally difficult to find. The Penn SoMe+EHR Bank links status updates, going back 5 years, with participant medical records in the University of Pennsylvania Health System, which go back a decade. Table 3 shows the size of data sets we will work with in the workshop [18], while Table 4 shows the size of supporting Twitter data from previously published work [6, 8].</p> <p>Despite the numerous challenges presented by our data and proposed approach, we also have reason to believe that achieving our stated goals will be feasible. Figure 5 demonstrates the accuracy with which our previous work [7] is able to model ten mental health conditions based on language modeling alone. Figure 6 demonstrates that change in language can be modeled over time, at an individual-level basis. Lastly, preliminary results within the SoMe+EHR Bank indicate that a diagnosis of anxiety can be predicted by one’s social media topics better than a model combining key demographic variables (age, gender, and race).</p> <table align="center"> <tbody> <tr> <td><div id="attachment_9704" style="width: 310px" class="wp-caption aligncenter"><a href="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5.jpg" rel="attachment wp-att-9704"><img loading="lazy" decoding="async" aria-describedby="caption-attachment-9704" class="wp-image-9704 size-medium" src="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5-300x300.jpg" alt="Figure 5: ROC curves for distinguishing diagnosed from control users, for ten disorders as examined in [15], with anxiety and eating disorders highlighted as two of the proposed conditions of study for this workshop. Chance performance is indicated by the black diagonal line." width="300" height="300" srcset="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5-300x300.jpg 300w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5-150x150.jpg 150w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5-180x180.jpg 180w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5-32x32.jpg 32w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5-64x64.jpg 64w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5-96x96.jpg 96w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5-128x128.jpg 128w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig5.jpg 750w" sizes="auto, (max-width: 300px) 100vw, 300px" /></a><p id="caption-attachment-9704" class="wp-caption-text">Figure 5: ROC curves for distinguishing diagnosed from control users, for ten disorders as examined in [15], with anxiety and eating disorders highlighted as two of the proposed conditions of study for this workshop. Chance performance is indicated by the black diagonal line.</p></div></td> <td> <p><div id="attachment_9697" style="width: 310px" class="wp-caption aligncenter"><a href="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig6.png" rel="attachment wp-att-9697"><img loading="lazy" decoding="async" aria-describedby="caption-attachment-9697" class="wp-image-9697 size-medium" src="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig6-300x212.png" alt="Figure 6: Timeline of the social media (Twitter) posts of 4 users—two users who attempted suicide (blue) and their age- and gender-matched controls (green)—scored by a character-based language model trained on the language of Twitter users prior to a suicide attempt." width="300" height="212" srcset="https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig6-300x212.png 300w, https://www.clsp.jhu.edu/wp-content/uploads/2016/03/SchwartzFig6.png 703w" sizes="auto, (max-width: 300px) 100vw, 300px" /></a><p id="caption-attachment-9697" class="wp-caption-text">Figure 6: Timeline of the social media (Twitter) posts of 4 users—two users who attempted suicide (blue) and their age- and gender-matched controls (green)—scored by a character-based language model trained on the language of Twitter users prior to a suicide attempt.</p></div></td> </tr> </tbody> </table> <p> </p> <h6>Goals and Outcomes</h6> <p>The overarching goal of the proposed workshop is to develop a better understanding of how to track mental health and wellness over time, with direct comparisons to clinical measurements and outcomes. Additionally, we expect to lay the foundation for further research into the temporal components of long-term mental health conditions. Information at this granularity, scale, and with clinical validation has never before been available, but can be the seed for revolution in mental health, wellbeing, and the scientific understanding of our selves.</p> <p> </p> <table id="tablepress-74" class="tablepress tablepress-id-74"> <thead> <tr class="row-1"> <th class="column-1">Team Members</th><th class="column-2"></th> </tr> </thead> <tbody class="row-striping row-hover"> <tr class="row-2"> <td class="column-1"><strong>Team Leader</strong></td><td class="column-2"></td> </tr> <tr class="row-3"> <td class="column-1">Kristy Hollingshead</td><td class="column-2">Institute for Human and Machine Cognition</td> </tr> <tr class="row-4"> <td class="column-1"><strong>Senior Members</strong></td><td class="column-2"></td> </tr> <tr class="row-5"> <td class="column-1">H. Andrew Schwartz</td><td class="column-2">Stony Brook University</td> </tr> <tr class="row-6"> <td class="column-1">Glen Coppersmith</td><td class="column-2">Qntfy</td> </tr> <tr class="row-7"> <td class="column-1">Dirk Hovy</td><td class="column-2">University of Copenhagen</td> </tr> <tr class="row-8"> <td class="column-1">Raina Merchant</td><td class="column-2">University of Pennsylvania</td> </tr> <tr class="row-9"> <td class="column-1"><strong>Graduate Students</strong></td><td class="column-2"></td> </tr> <tr class="row-10"> <td class="column-1">Patrick Crutchley</td><td class="column-2">University of Pennsylvania</td> </tr> <tr class="row-11"> <td class="column-1">Fatemeh Almodaresi</td><td class="column-2">Stony Brook University</td> </tr> <tr class="row-12"> <td class="column-1">Adrian Benton</td><td class="column-2">Johns Hopkins University</td> </tr> <tr class="row-13"> <td class="column-1">Jeff Craley</td><td class="column-2">Johns Hopkins University</td> </tr> <tr class="row-14"> <td class="column-1"><strong>Undergraduate Students</strong></td><td class="column-2"></td> </tr> <tr class="row-15"> <td class="column-1">Amos Kim</td><td class="column-2">University of Colorado Boluder</td> </tr> <tr class="row-16"> <td class="column-1">Bu Sun Kim</td><td class="column-2">University of Colorado Boulder</td> </tr> <tr class="row-17"> <td class="column-1"><strong>Senior Affiliates (Part-time Members)</strong></td><td class="column-2"></td> </tr> <tr class="row-18"> <td class="column-1">Molly Ireland</td><td class="column-2">TexTech</td> </tr> <tr class="row-19"> <td class="column-1">Masoud Rohizadeh</td><td class="column-2">Stony Brook University</td> </tr> <tr class="row-20"> <td class="column-1">Lyle Ungar</td><td class="column-2">University of Pennsylvania</td> </tr> <tr class="row-21"> <td class="column-1">Meg Mitchell</td><td class="column-2">Microsoft Research</td> </tr> <tr class="row-22"> <td class="column-1">Andreas Andreou</td><td class="column-2">Johns Hopkins University</td> </tr> </tbody> </table> </div> </div> <div class="span4"> <div class="sidebar right-sidebar"> <div id="text-7" class="widget widget_text"> <div class="textwidget"><a href="/cdn-cgi/l/email-protection#4c3f35213c2d0c20253f383f62262462292839733f392e26292f38713f392e3f2f3e252e296c2f203f3c3f292125222d3e3f">Subscribe to the CLSP Seminars Mailing List</a></div> </div><div id="ai1ec_agenda_widget-6" class="widget widget_ai1ec_agenda_widget"> <h3 class="widget-title">Upcoming Seminars</h3> <style>  </style> <div class="timely ai1ec-agenda-widget-view ai1ec-clearfix"> <div> <div class="ai1ec-date ai1ec-today"> <a class="ai1ec-date-title ai1ec-load-view" href="https://www.clsp.jhu.edu/seminars/action~oneday/exact_date~11-22-2024/"> <div class="ai1ec-month">Nov</div> <div class="ai1ec-day">22</div> <div class="ai1ec-weekday">Fri</div> </a> <div class="ai1ec-date-events"> <div class="ai1ec-event ai1ec-event-id-28122 ai1ec-event-instance-id-3477 "> <a href="https://www.clsp.jhu.edu/events/chenhao-tan-university-of-chicago-beyond-human-preferences-use-human-goals-to-guide-ai-towards-complementary-ai-2/?instance_id=3477" class="ai1ec-popup-trigger ai1ec-load-event"> <span class="ai1ec-event-time"> 12:00 pm </span> <span class="ai1ec-event-title"> Chenhao Tan (University of Chica... <span class="ai1ec-event-location" >@ Hackerman Hall B17</span> </span> </a> <div class="ai1ec-popover ai1ec-popup ai1ec-event-instance-id-3477"> <span class="ai1ec-popup-title"> <a href="https://www.clsp.jhu.edu/events/chenhao-tan-university-of-chicago-beyond-human-preferences-use-human-goals-to-guide-ai-towards-complementary-ai-2/?instance_id=3477" class="ai1ec-load-event" >Chenhao Tan (University of Chica...</a> <span class="ai1ec-event-location" >@ Hackerman Hall B17</span> </span> <div class="ai1ec-event-time"> Nov 22 @ 12:00 pm – 1:15 pm </div> <div class="ai1ec-popup-excerpt">Abstract Human preferences have been the main component in guiding pretrained AI. In this talk, I argue that human preferences are often insufficient for complementing human intelligence and demonstrate the key role of human goals[...]</div> </div> </div> </div> </div> </div> <div class="ai1ec-subscribe-buttons-widget"> <a class="ai1ec-btn ai1ec-btn-default ai1ec-btn-xs ai1ec-pull-right ai1ec-calendar-link" href="https://www.clsp.jhu.edu/seminars/"> View Calendar <i class="ai1ec-fa ai1ec-fa-arrow-right"></i> </a> <div class="ai1ec-subscribe-dropdown ai1ec-dropdown ai1ec-btn ai1ec-btn-default ai1ec-btn-xs"> <span role="button" class="ai1ec-dropdown-toggle ai1ec-subscribe" data-toggle="ai1ec-dropdown"> <i class="ai1ec-fa ai1ec-icon-rss ai1ec-fa-lg ai1ec-fa-fw"></i> <span class="ai1ec-hidden-xs"> Add <span class="ai1ec-caret"></span> </span> </span> <ul class="ai1ec-dropdown-menu ai1ec-pull-left" role="menu"> <li> <a class="ai1ec-tooltip-trigger ai1ec-tooltip-auto" target="_blank" data-placement="right" title="Copy this URL for your own Timely calendar or click to add to your rich-text calendar" href="http://www.clsp.jhu.edu/?plugin=all-in-one-event-calendar&controller=ai1ec_exporter_controller&action=export_events"> <i class="ai1ec-fa ai1ec-fa-lg ai1ec-fa-fw ai1ec-icon-timely"></i> Add to Timely Calendar </a> </li> <li> <a class="ai1ec-tooltip-trigger ai1ec-tooltip-auto" target="_blank" data-placement="right" title="Subscribe to this calendar in your Google Calendar" href="https://www.google.com/calendar/render?cid=http%3A%2F%2Fwww.clsp.jhu.edu%2F%3Fplugin%3Dall-in-one-event-calendar%26controller%3Dai1ec_exporter_controller%26action%3Dexport_events%26no_html%3Dtrue%26%26"> <i class="ai1ec-fa ai1ec-icon-google ai1ec-fa-lg ai1ec-fa-fw"></i> Add to Google </a> </li> <li> <a class="ai1ec-tooltip-trigger ai1ec-tooltip-auto" target="_blank" data-placement="right" title="Subscribe to this calendar in MS Outlook" href="webcal://www.clsp.jhu.edu/?plugin=all-in-one-event-calendar&controller=ai1ec_exporter_controller&action=export_events&no_html=true"> <i class="ai1ec-fa ai1ec-icon-windows ai1ec-fa-lg ai1ec-fa-fw"></i> Add to Outlook </a> </li> <li> <a class="ai1ec-tooltip-trigger ai1ec-tooltip-auto" target="_blank" data-placement="right" title="Subscribe to this calendar in Apple Calendar/iCal" href="webcal://www.clsp.jhu.edu/?plugin=all-in-one-event-calendar&controller=ai1ec_exporter_controller&action=export_events&no_html=true"> <i class="ai1ec-fa ai1ec-icon-apple ai1ec-fa-lg ai1ec-fa-fw"></i> Add to Apple Calendar </a> </li> <li> <a class="ai1ec-tooltip-trigger ai1ec-tooltip-auto" data-placement="right" title="Subscribe to this calendar in another plain-text calendar" href="http://www.clsp.jhu.edu/?plugin=all-in-one-event-calendar&controller=ai1ec_exporter_controller&action=export_events&no_html=true"> <i class="ai1ec-fa ai1ec-icon-calendar ai1ec-fa-fw"></i> Add to other calendar </a> </li> <li> <a class="ai1ec-tooltip-trigger ai1ec-tooltip-auto" data-placement="right" title="" href="http://www.clsp.jhu.edu/?plugin=all-in-one-event-calendar&controller=ai1ec_exporter_controller&action=export_events&xml=true"> <i class="ai1ec-fa ai1ec-fa-file-text ai1ec-fa-lg ai1ec-fa-fw"></i> Export to XML </a> </li> </ul> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> <footer id="page-footer"> <div class="ribbon"> <div class="container"> <div id="block-12" class="widget widget_block"><br></div><div id="block-11" class="widget widget_block"> <hr class="wp-block-separator has-alpha-channel-opacity"/> </div><div id="block-13" class="widget widget_block"> <h4 class="has-text-align-center wp-block-heading">Seminar Videos</h4> </div><div id="block-5" class="widget widget_block"> <div id="sb_youtube_sbyUCWWiAEF7PMkOK0rwGITIg5" class="sb_youtube sby_layout_grid sby_col_5 sby_mob_col_1 sby_palette_inherit sby_width_resp" data-feedid="sby_UCWWiAEF7PMk-OK0-rwGITIg#5" data-shortcode-atts="{"feed":"4"}" data-cols="5" data-colsmobile="1" data-num="5" data-nummobile="5" data-channel-subscribers="121 subscribers" data-subscribe-btn="1" data-subscribe-btn-text="Subscribe" data_channel_header_colors ="{"channelName":"","subscribeCount":"","buttonBackground":"","buttonText":""}" data-sby-flags="resizeDisable" data-postid="9601" data-sby-supports-lightbox="1" data-videocardlayout="vertical" > <div class="sby_items_wrap" style="padding: 5px;"> <div class="sby_item sby_new sby_transition" id="sby_UCWWiAEF7PMk-OK0-rwGITIg_cf4apIcnPtU" data-date="1732073606" data-video-id="cf4apIcnPtU"> <div class="sby_inner_item"> <div class="sby_video_thumbnail_wrap sby_item_video_thumbnail_wrap"> <a class="sby_video_thumbnail sby_item_video_thumbnail" href="https://www.youtube.com/watch?v=cf4apIcnPtU" target="_blank" rel="noopener" data-full-res="https://i4.ytimg.com/vi/cf4apIcnPtU/maxresdefault.jpg" data-img-src-set="{"120":"https:\/\/i4.ytimg.com\/vi\/cf4apIcnPtU\/default.jpg","320":"https:\/\/i4.ytimg.com\/vi\/cf4apIcnPtU\/mqdefault.jpg","480":"https:\/\/i4.ytimg.com\/vi\/cf4apIcnPtU\/hqdefault.jpg","640":"https:\/\/i4.ytimg.com\/vi\/cf4apIcnPtU\/sddefault.jpg"}" data-video-id="cf4apIcnPtU" data-video-title="Generative World Explorer"> <img decoding="async" src="https://www.clsp.jhu.edu/wp-content/plugins/feeds-for-youtube/img/placeholder.png" alt="Project page: https://generative-world-explorer.github.io/ Paper: https://arxiv.org/abs/2411.11844 Abstract: Planning with partial observation is a central challenge in embodied AI. A majority of prior works have tackled this challenge by developing agents that physically explore their environment to update their beliefs about the world state. In contrast, humans can imagine unseen parts of the world through a mental exploration and revise their beliefs with imagined observations. Such updated beliefs can allow them to make more informed decisions, without necessitating the physical exploration of the world at all times. To achieve this human-like ability, we introduce the Generative World Explorer (Genex), an egocentric world exploration framework that allows an agent to mentally explore a large-scale 3D world (e.g., urban scenes) and acquire imagined observations to update its belief. This updated belief will then help the agent to make a more informed decision at the current step. To train Genex, we create a synthetic urban scene dataset, Genex-DB. Our experimental results demonstrate that (1) Genex can generate high-quality and consistent observations during long-horizon exploration of a large virtual physical world and (2) the beliefs updated with the generated observations can inform an existing decision-making model (e.g., an LLM agent) to make better plans."> <div class="sby_thumbnail_hover sby_item_video_thumbnail_hover"> <div class="sby_thumbnail_hover_inner"> <span class="sby_video_title" >Generative World Explorer</span> </div> </div> <div class="sby_play_btn" > <span class="sby_play_btn_bg"></span> <svg aria-hidden="true" focusable="false" data-prefix="fab" data-icon="youtube" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" class="svg-inline--fa fa-youtube fa-w-18"><path fill="currentColor" d="M549.655 124.083c-6.281-23.65-24.787-42.276-48.284-48.597C458.781 64 288 64 288 64S117.22 64 74.629 75.486c-23.497 6.322-42.003 24.947-48.284 48.597-11.412 42.867-11.412 132.305-11.412 132.305s0 89.438 11.412 132.305c6.281 23.65 24.787 41.5 48.284 47.821C117.22 448 288 448 288 448s170.78 0 213.371-11.486c23.497-6.321 42.003-24.171 48.284-47.821 11.412-42.867 11.412-132.305 11.412-132.305s0-89.438-11.412-132.305zm-317.51 213.508V175.185l142.739 81.205-142.739 81.201z" class=""></path></svg> </div> <span class="sby_loader sby_hidden" style="background-color: rgb(255, 255, 255);"></span> </a> </div> </div> </div><div class="sby_item sby_new sby_transition" id="sby_UCWWiAEF7PMk-OK0-rwGITIg_d5p6IhagfXM" data-date="1731992425" data-video-id="d5p6IhagfXM"> <div class="sby_inner_item"> <div class="sby_video_thumbnail_wrap sby_item_video_thumbnail_wrap"> <a class="sby_video_thumbnail sby_item_video_thumbnail" href="https://www.youtube.com/watch?v=d5p6IhagfXM" target="_blank" rel="noopener" data-full-res="https://i1.ytimg.com/vi/d5p6IhagfXM/maxresdefault.jpg" data-img-src-set="{"120":"https:\/\/i1.ytimg.com\/vi\/d5p6IhagfXM\/default.jpg","320":"https:\/\/i1.ytimg.com\/vi\/d5p6IhagfXM\/mqdefault.jpg","480":"https:\/\/i1.ytimg.com\/vi\/d5p6IhagfXM\/hqdefault.jpg","640":"https:\/\/i1.ytimg.com\/vi\/d5p6IhagfXM\/sddefault.jpg"}" data-video-id="d5p6IhagfXM" data-video-title="Automatically Deriving Adjectival Scales – Marie-Catherine de Marneffe (OSU) - 2013"> <img decoding="async" src="https://www.clsp.jhu.edu/wp-content/plugins/feeds-for-youtube/img/placeholder.png" alt="December 6, 2013 Abstract In this talk, I will discuss how to automatically derive the orderings and meanings of gradable adjectives. To determine whether the intended answer is “yes” or “no” in a dialogue such as “Was the movie wonderful? It was worth seeing”, we need to evaluate how “worth seeing” relates to “wonderful”. Can we automatically learn from real texts the scalar orderings people assign to these modifiers? I will show how we can exploit the availability of large amounts of text on the web (such as online reviews ratings) to approximate these orderings. Then I will turn to neural network language models. I will show that continuous space word representations extracted from such models can be used to derive adjectival scales of high quality, emphasizing that neural network language models do capture semantic regularities. I evaluate the quality of the adjectival scales on several datasets. Next, I will briefly turn to biomedical data: what does it mean to show “severe symptoms of cardiac disease” or “mild pulmonary symptoms”? I will outline work in progress targeting the meaning of gradable adjectives in that domain. Not only do we want to get an ordering between such adjectives, but we also want to learn what counts as “severe” or “mild” symptoms of a disease. Biography Marie-Catherine de Marneffe is an assistant professor in Linguistics at The Ohio State University. She received her PhD from Stanford University in December 2012 under the supervision of Christopher D. Manning. She is developing computational linguistic methods that capture what is conveyed by speakers beyond the literal meaning of the words they say. Primarily she wants to ground meanings in corpus data, and show how such meanings can drive pragmatic inference. She has also worked on Recognizing Textual Entailment and contributed to defining the Stanford Dependencies representation, which is designed to be a practical representation of grammatical relations and predicate argument structure"> <div class="sby_thumbnail_hover sby_item_video_thumbnail_hover"> <div class="sby_thumbnail_hover_inner"> <span class="sby_video_title" >Automatically Deriving Adjectival Scales – Marie-Catherine de Marneffe (OSU) - 2013</span> </div> </div> <div class="sby_play_btn" > <span class="sby_play_btn_bg"></span> <svg aria-hidden="true" focusable="false" data-prefix="fab" data-icon="youtube" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" class="svg-inline--fa fa-youtube fa-w-18"><path fill="currentColor" d="M549.655 124.083c-6.281-23.65-24.787-42.276-48.284-48.597C458.781 64 288 64 288 64S117.22 64 74.629 75.486c-23.497 6.322-42.003 24.947-48.284 48.597-11.412 42.867-11.412 132.305-11.412 132.305s0 89.438 11.412 132.305c6.281 23.65 24.787 41.5 48.284 47.821C117.22 448 288 448 288 448s170.78 0 213.371-11.486c23.497-6.321 42.003-24.171 48.284-47.821 11.412-42.867 11.412-132.305 11.412-132.305s0-89.438-11.412-132.305zm-317.51 213.508V175.185l142.739 81.205-142.739 81.201z" class=""></path></svg> </div> <span class="sby_loader sby_hidden" style="background-color: rgb(255, 255, 255);"></span> </a> </div> </div> </div><div class="sby_item sby_new sby_transition" id="sby_UCWWiAEF7PMk-OK0-rwGITIg_uf6PSqy3WPc" data-date="1731645479" data-video-id="uf6PSqy3WPc"> <div class="sby_inner_item"> <div class="sby_video_thumbnail_wrap sby_item_video_thumbnail_wrap"> <a class="sby_video_thumbnail sby_item_video_thumbnail" href="https://www.youtube.com/watch?v=uf6PSqy3WPc" target="_blank" rel="noopener" data-full-res="https://i2.ytimg.com/vi/uf6PSqy3WPc/maxresdefault.jpg" data-img-src-set="{"120":"https:\/\/i2.ytimg.com\/vi\/uf6PSqy3WPc\/default.jpg","320":"https:\/\/i2.ytimg.com\/vi\/uf6PSqy3WPc\/mqdefault.jpg","480":"https:\/\/i2.ytimg.com\/vi\/uf6PSqy3WPc\/hqdefault.jpg","640":"https:\/\/i2.ytimg.com\/vi\/uf6PSqy3WPc\/sddefault.jpg"}" data-video-id="uf6PSqy3WPc" data-video-title="Evaluating Unlearning and Memorization via Compression -- Zhili Feng (CMU)"> <img decoding="async" src="https://www.clsp.jhu.edu/wp-content/plugins/feeds-for-youtube/img/placeholder.png" alt="Zhili Feng: https://zhilif.github.io/"> <div class="sby_thumbnail_hover sby_item_video_thumbnail_hover"> <div class="sby_thumbnail_hover_inner"> <span class="sby_video_title" >Evaluating Unlearning and Memorization via Compression -- Zhili Feng (CMU)</span> </div> </div> <div class="sby_play_btn" > <span class="sby_play_btn_bg"></span> <svg aria-hidden="true" focusable="false" data-prefix="fab" data-icon="youtube" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" class="svg-inline--fa fa-youtube fa-w-18"><path fill="currentColor" d="M549.655 124.083c-6.281-23.65-24.787-42.276-48.284-48.597C458.781 64 288 64 288 64S117.22 64 74.629 75.486c-23.497 6.322-42.003 24.947-48.284 48.597-11.412 42.867-11.412 132.305-11.412 132.305s0 89.438 11.412 132.305c6.281 23.65 24.787 41.5 48.284 47.821C117.22 448 288 448 288 448s170.78 0 213.371-11.486c23.497-6.321 42.003-24.171 48.284-47.821 11.412-42.867 11.412-132.305 11.412-132.305s0-89.438-11.412-132.305zm-317.51 213.508V175.185l142.739 81.205-142.739 81.201z" class=""></path></svg> </div> <span class="sby_loader sby_hidden" style="background-color: rgb(255, 255, 255);"></span> </a> </div> </div> </div><div class="sby_item sby_new sby_transition" id="sby_UCWWiAEF7PMk-OK0-rwGITIg_X_U_jdXXfv0" data-date="1731004488" data-video-id="X_U_jdXXfv0"> <div class="sby_inner_item"> <div class="sby_video_thumbnail_wrap sby_item_video_thumbnail_wrap"> <a class="sby_video_thumbnail sby_item_video_thumbnail" href="https://www.youtube.com/watch?v=X_U_jdXXfv0" target="_blank" rel="noopener" data-full-res="https://i1.ytimg.com/vi/X_U_jdXXfv0/maxresdefault.jpg" data-img-src-set="{"120":"https:\/\/i1.ytimg.com\/vi\/X_U_jdXXfv0\/default.jpg","320":"https:\/\/i1.ytimg.com\/vi\/X_U_jdXXfv0\/mqdefault.jpg","480":"https:\/\/i1.ytimg.com\/vi\/X_U_jdXXfv0\/hqdefault.jpg","640":"https:\/\/i1.ytimg.com\/vi\/X_U_jdXXfv0\/sddefault.jpg"}" data-video-id="X_U_jdXXfv0" data-video-title="AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies (EMNLP 2024)"> <img decoding="async" src="https://www.clsp.jhu.edu/wp-content/plugins/feeds-for-youtube/img/placeholder.png" alt="Paper: https://arxiv.org/abs/2402.12370 Abstract: Humans regularly engage in analogical thinking, relating personal experiences to current situations (X is analogous to Y because of Z). Analogical thinking allows humans to solve problems in creative ways, grasp difficult concepts, and articulate ideas more effectively. Can language models (LMs) do the same? To answer this question, we propose AnaloBench, a benchmark to determine analogical reasoning ability in LMs. Our benchmarking approach focuses on aspects of this ability that are common among humans: (i) recalling related experiences from a large amount of information, and (ii) applying analogical reasoning to complex and lengthy scenarios. We test a broad collection of proprietary models (e.g., GPT family, Claude V2) and open source models such as LLaMA2. As in prior results, scaling up LMs results in some performance boosts. Surprisingly, scale offers minimal gains when, (i) analogies involve lengthy scenarios, or (ii) recalling relevant scenarios from a large pool of information, a process analogous to finding a needle in a haystack. We hope these observations encourage further research in this field."> <div class="sby_thumbnail_hover sby_item_video_thumbnail_hover"> <div class="sby_thumbnail_hover_inner"> <span class="sby_video_title" >AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies (EMNLP 2024)</span> </div> </div> <div class="sby_play_btn" > <span class="sby_play_btn_bg"></span> <svg aria-hidden="true" focusable="false" data-prefix="fab" data-icon="youtube" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" class="svg-inline--fa fa-youtube fa-w-18"><path fill="currentColor" d="M549.655 124.083c-6.281-23.65-24.787-42.276-48.284-48.597C458.781 64 288 64 288 64S117.22 64 74.629 75.486c-23.497 6.322-42.003 24.947-48.284 48.597-11.412 42.867-11.412 132.305-11.412 132.305s0 89.438 11.412 132.305c6.281 23.65 24.787 41.5 48.284 47.821C117.22 448 288 448 288 448s170.78 0 213.371-11.486c23.497-6.321 42.003-24.171 48.284-47.821 11.412-42.867 11.412-132.305 11.412-132.305s0-89.438-11.412-132.305zm-317.51 213.508V175.185l142.739 81.205-142.739 81.201z" class=""></path></svg> </div> <span class="sby_loader sby_hidden" style="background-color: rgb(255, 255, 255);"></span> </a> </div> </div> </div><div class="sby_item sby_new sby_transition" id="sby_UCWWiAEF7PMk-OK0-rwGITIg_JVhXsqlzsWI" data-date="1730935150" data-video-id="JVhXsqlzsWI"> <div class="sby_inner_item"> <div class="sby_video_thumbnail_wrap sby_item_video_thumbnail_wrap"> <a class="sby_video_thumbnail sby_item_video_thumbnail" href="https://www.youtube.com/watch?v=JVhXsqlzsWI" target="_blank" rel="noopener" data-full-res="https://i3.ytimg.com/vi/JVhXsqlzsWI/maxresdefault.jpg" data-img-src-set="{"120":"https:\/\/i3.ytimg.com\/vi\/JVhXsqlzsWI\/default.jpg","320":"https:\/\/i3.ytimg.com\/vi\/JVhXsqlzsWI\/mqdefault.jpg","480":"https:\/\/i3.ytimg.com\/vi\/JVhXsqlzsWI\/hqdefault.jpg","640":"https:\/\/i3.ytimg.com\/vi\/JVhXsqlzsWI\/sddefault.jpg"}" data-video-id="JVhXsqlzsWI" data-video-title="Parisa Rashidi: AI and Pervasive Sensing: The Silent Guardians of Tomorrow's ICU"> <img decoding="async" src="https://www.clsp.jhu.edu/wp-content/plugins/feeds-for-youtube/img/placeholder.png" alt="Abstract In the high-stakes world of critical care, every second counts. Traditional manual patient monitoring, while effective, strains our healthcare system’s resources. Nurses, already stretched thin, repetitively assess acute care indices like physical function. Meanwhile, crucial patient data— cognitive function, sleep quality, and environmental factors—often slip through the cracks or lack granular detail. Artificial Intelligence (AI) and pervasive sensing promise to revolutionize patient care in the Intensive Care Unit (ICU). By seamlessly integrating with continuous physiologic measurements and clinical data, they offer a real-time, interpretable, and precise assessment of patient condition. We have developed AI system that augment traditional clinical data with pervasive sensing, capturing previously unmeasured or manually recorded acute care indices. This breakthrough forms the cornerstone of our vision: to sense, quantify, and communicate a patient’s condition with unprecedented accuracy and clarity. This presentation will unveil the potential of pervasive sensing and AI in acute care settings. We’ll explore how these technologies are set to reshape current medical practices and spark a dialogue about the integration of intelligent, pervasive health technology in hospitals. Biography Dr. Parisa Rashidi is the founding co-director of the Intelligent Clinical Care Center (IC3) at the University of Florida (UF) and a professor at the J. Crayton Pruitt Family Department of Biomedical Engineering (BME). She is also affiliated with the Electrical & Computer Engineering (ECE) and Computer and Information Science and Engineering (CISE) departments. Her research aims to bridge the gap between machine learning and patient care. Dr. Rashidi is a fellow of the American Institute for Medical and Biological Engineering (AIMBE), the National Science Foundation (NSF) CAREER awardee, the National Institute of Health (NIH) Trailblazer Awardee, Herbert Wertheim College of Engineering Leadership Excellence Awardee, Herbert Wertheim College of Engineering Assistant Professor Excellence Awardee, and a recipient of the UF term professorship. She also received UF’s Provost Excellence Award for assistant professors; with more than 500 tenure-track assistant professors at UF, Dr. Rashidi is one of only 10 to receive this award. She was invited by the National Academy of Engineering (NAE) as one of only 38 outstanding US engineers under 45 to participate in the EU-US Frontiers of Engineering (FOE) Meeting. To date, she has authored 170+ peer-reviewed publications. She has chaired several workshops and symposiums on intelligent health systems and has served on the program committee of 20+ conferences. Dr. Rashidi’s research has been supported by local, state, and federal grants, including awards from the National Institutes of Health (NIBIB, NCI, and NIGMS) and the National Science Foundation (NSF)."> <div class="sby_thumbnail_hover sby_item_video_thumbnail_hover"> <div class="sby_thumbnail_hover_inner"> <span class="sby_video_title" >Parisa Rashidi: AI and Pervasive Sensing: The Silent Guardians of Tomorrow's ICU</span> </div> </div> <div class="sby_play_btn" > <span class="sby_play_btn_bg"></span> <svg aria-hidden="true" focusable="false" data-prefix="fab" data-icon="youtube" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" class="svg-inline--fa fa-youtube fa-w-18"><path fill="currentColor" d="M549.655 124.083c-6.281-23.65-24.787-42.276-48.284-48.597C458.781 64 288 64 288 64S117.22 64 74.629 75.486c-23.497 6.322-42.003 24.947-48.284 48.597-11.412 42.867-11.412 132.305-11.412 132.305s0 89.438 11.412 132.305c6.281 23.65 24.787 41.5 48.284 47.821C117.22 448 288 448 288 448s170.78 0 213.371-11.486c23.497-6.321 42.003-24.171 48.284-47.821 11.412-42.867 11.412-132.305 11.412-132.305s0-89.438-11.412-132.305zm-317.51 213.508V175.185l142.739 81.205-142.739 81.201z" class=""></path></svg> </div> <span class="sby_loader sby_hidden" style="background-color: rgb(255, 255, 255);"></span> </a> </div> </div> </div> </div> <div class="sby_footer"> <a class="sby_load_btn" href="javascript:void(0);" > <span class="sby_btn_text" >Load More...</span> <span class="sby_loader sby_hidden" style="background-color: rgb(255, 255, 255);"></span> </a> <span class="sby_follow_btn" > <a href="https://www.youtube.com/channel/UCWWiAEF7PMk-OK0-rwGITIg/" target="_blank" rel="noopener" > <svg aria-hidden="true" focusable="false" data-prefix="fab" data-icon="youtube" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" class="svg-inline--fa fa-youtube fa-w-18"><path fill="currentColor" d="M549.655 124.083c-6.281-23.65-24.787-42.276-48.284-48.597C458.781 64 288 64 288 64S117.22 64 74.629 75.486c-23.497 6.322-42.003 24.947-48.284 48.597-11.412 42.867-11.412 132.305-11.412 132.305s0 89.438 11.412 132.305c6.281 23.65 24.787 41.5 48.284 47.821C117.22 448 288 448 288 448s170.78 0 213.371-11.486c23.497-6.321 42.003-24.171 48.284-47.821 11.412-42.867 11.412-132.305 11.412-132.305s0-89.438-11.412-132.305zm-317.51 213.508V175.185l142.739 81.205-142.739 81.201z" class=""></path></svg> <span > Subscribe </span> </a> </span> </div> </div> <style type="text/css">#sb_youtube_sbyUCWWiAEF7PMkOK0rwGITIg5 .sby_caption_wrap .sby_caption { font-size: 13px !important}#sb_youtube_sbyUCWWiAEF7PMkOK0rwGITIg5 .sby_follow_btn a:hover { box-shadow:inset 0 0 10px 20px rgb(255, 255, 255, .25) !important}#sb_youtube_sbyUCWWiAEF7PMkOK0rwGITIg5[data-videostyle=boxed] .sby_items_wrap .sby_item .sby_inner_item { background-color: #ffffff !important}</style></div> </div> </div> <div class="container"> <div class="row jhu-meta"> <div class="span6 university-info"> <div class="address"> <div> <p><img decoding="async" src="https://engineering.jhu.edu/wp-content/themes/wse/assets/images/jhu-logo-white.png" alt="Johns Hopkins University" /></p> <h4>Johns Hopkins University, Whiting School of Engineering</h4> <p>Center for Language and Speech Processing<br /> Hackerman 226<br /> 3400 North Charles Street, Baltimore, MD 21218-2680</p> </div> </div> <ul class="contact-info"> <li> <i class="icon-iphone"></i> <span class="value"> (410) 516-4237 </span> </li> <li> <i class="icon-wse-email"></i> <span class="value"> <a href="/cdn-cgi/l/email-protection#27444b545746434a4e49674b4e545354094d484f49544f48574c4e495409424352"> <span class="__cf_email__" data-cfemail="98fbf4ebe8f9fcf5f1f6d8f4f1ebecebb6f2f7f0f6ebf0f7e8f3f1f6ebb6fdfced">[email protected]</span> </a> </span> </li> </ul> </div> <div class="span3"> <nav id="footer-nav"> <div class="menu-footer-container"><ul id="menu-footer" class="menu"><li id="menu-item-4020" class="menu-item menu-item-type-custom menu-item-object-custom menu-item-4020 has-icon "><a href="https://engineering.jhu.edu"><span class="fontawesome-text">Whiting School of Engineering</span> <i class="icon-external"> </i></a></li> <li id="menu-item-4021" class="menu-item menu-item-type-custom menu-item-object-custom menu-item-4021 has-icon "><a href="http://jhu.edu"><span class="fontawesome-text">Johns Hopkins University</span> <i class="icon-external"> </i></a></li> </ul></div> </nav> <nav id="copyright-nav"> <ul id="menu-copyright" class="menu"><li id="menu-item-16222" class="menu-item menu-item-type-custom menu-item-object-custom menu-item-16222 has-icon "><a href="https://it.johnshopkins.edu/policies/privacystatement"><span class="fontawesome-text">Privacy Statement</span> <i class="icon-external"> </i></a></li> <li id="menu-item-4022" class="menu-item menu-item-type-custom menu-item-object-custom menu-item-4022 has-icon "><a href="http://webapps.jhu.edu/jhuniverse/administration/minutes_policies_reports/policies/copyright/"><span class="fontawesome-text">Legal</span> <i class="icon-external"> </i></a></li> </ul> </nav> <div id="copyright"> © 2024 Johns Hopkins University </div> </div> <div class="span3"> <ul class="social-icons"> <li> <a href="https://www.facebook.com/JHUCLSP/" target="_blank" title="Facebook"> <i class="icon-facebook"></i> </a> </li> <li> <a href="https://twitter.com/jhuclsp" target="_blank" title="Twitter"> <i class="icon-twitter"></i> </a> </li> </ul> </div> </div> </div> </footer> <script data-cfasync="false" src="/cdn-cgi/scripts/5c5dd728/cloudflare-static/email-decode.min.js"></script><script type="text/javascript"> </script> <link rel='stylesheet' id='academicons-css' href='https://www.clsp.jhu.edu/wp-content/plugins/teachpress/includes/academicons/css/academicons.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='font-awesome-css' href='https://www.clsp.jhu.edu/wp-content/plugins/teachpress/includes/fontawesome/css/all.min.css?ver=0db417805d51931f0f17316a3e6b0de3' type='text/css' media='all' /> <link rel='stylesheet' id='tablepress-default-css' href='https://www.clsp.jhu.edu/wp-content/plugins/tablepress/css/build/default.css?ver=3.0' type='text/css' media='all' /> <link rel='stylesheet' id='sby_styles-css' href='https://www.clsp.jhu.edu/wp-content/plugins/feeds-for-youtube/css/sb-youtube.min.css?ver=2.2.4' type='text/css' media='all' /> <script type="text/javascript" id="google_cse_v2-js-extra"> /* <![CDATA[ */ var scriptParams = {"google_search_engine_id":"012258670098148303364:_rdjmumnaxa"}; /* ]]> */ </script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/plugins/wp-google-search/assets/js/google_cse_v2.js?ver=1" id="google_cse_v2-js"></script> <script type="text/javascript" id="embedpress-front-js-extra"> /* <![CDATA[ */ var eplocalize = {"ajaxurl":"https:\/\/www.clsp.jhu.edu\/wp-admin\/admin-ajax.php","is_pro_plugin_active":"","nonce":"dcea2284ac"}; /* ]]> */ </script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/plugins/embedpress/assets/js/front.js?ver=4.1.3" id="embedpress-front-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/?ai1ec_render_js=common_frontend&is_backend=false&ver=3.0.0" id="ai1ec_requirejs-js"></script> <script type="text/javascript" id="sby_scripts-js-extra"> /* <![CDATA[ */ var sbyOptions = {"isAdmin":"","adminAjaxUrl":"https:\/\/www.clsp.jhu.edu\/wp-admin\/admin-ajax.php","placeholder":"https:\/\/www.clsp.jhu.edu\/wp-content\/plugins\/feeds-for-youtube\/img\/placeholder.png","placeholderNarrow":"https:\/\/www.clsp.jhu.edu\/wp-content\/plugins\/feeds-for-youtube\/img\/placeholder-narrow.png","lightboxPlaceholder":"https:\/\/www.clsp.jhu.edu\/wp-content\/plugins\/feeds-for-youtube\/img\/lightbox-placeholder.png","lightboxPlaceholderNarrow":"https:\/\/www.clsp.jhu.edu\/wp-content\/plugins\/feeds-for-youtube\/img\/lightbox-placeholder-narrow.png","autoplay":"1","semiEagerload":"","eagerload":"","nonce":"1cb41719d1","isPro":"","isCustomizer":""}; /* ]]> */ </script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/plugins/feeds-for-youtube/js/sb-youtube.min.js?ver=2.2.4" id="sby_scripts-js"></script> <script type="text/javascript" src="https://www.clsp.jhu.edu/wp-content/plugins/tablepress/js/jquery.datatables.min.js?ver=3.0" id="tablepress-datatables-js"></script> <script type="text/javascript">(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); ga('create', 'UA-42985538-1', 'jhu.edu'); ga('create', 'UA-69724146-2', 'auto'); ga('create', 'UA-82200180-1', 'auto', 'jhuGlobal', {'allowLinker' : true}); ga('require', 'linker'); ga('jhuGlobal.linker:autoLink', ['johnshopkins.edu', 'jh.edu']); ga('send', 'pageview'); ga('jhuGlobal.send', 'pageview'); /*<![CDATA[*/ (function() { var sz = document.createElement('script'); sz.type = 'text/javascript'; sz.async = true; sz.src = '//us2.siteimprove.com/js/siteanalyze_16739.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(sz, s); })(); /*]]>*/ </script> </div> </div> </div> <div class="phone-menu"> <div class="logo"> <img src="https://www.clsp.jhu.edu/wp-content/themes/wse/assets/images/wse-logo-white-vertical@2x.png" alt="Johns Hopkins University | Whiting School of Engineering" /> </div> <h1 class="site-title"> Center for Language and Speech Processing </h3> </div> </body>  </html>