Анализ сайта hyeonsukang.com
Основное Готовность: 55%
Домен
hyeonsukang.com
Состояние доменного имени
?
Проверяем корректность доменного имени и наличие технических проблем на уровне домена.
Домен второго уровня идеален для продвижения.
Отличный запоминающийся домен.
Ответ сервера
200 Успешный ответ
HTTP-код ответа и цепочка редиректов
?
Код 200 — страница доступна. Коды 3xx — редиректы (цепочки замедляют загрузку и размывают ссылочный вес). Коды 4xx/5xx — ошибки, поисковик не сможет проиндексировать страницу.
Сервер настроен корректно.
Цепочка редиректов:
http://hyeonsukang.com
302 Found
http://www.hyeonsukang.com/
200 OK
Безопасность
Сайт небезопасен
Использование HTTPS и SSL-сертификат
?
HTTPS — обязательный стандарт. Google и Яндекс отдают предпочтение защищённым сайтам. Отсутствие SSL или просроченный сертификат ведут к предупреждениям в браузере и снижению позиций.
На сайте не найден защищенный протокол ssl и сайт не открывается по https!
Не настроен HSTS (Strict-Transport-Security) — рекомендуется включить.
HTTP автоматически перенаправляется на HTTPS.
Поздравляем! Сайт не содержится в реестре РКН.
Кодировка
utf-8
Кодировка символов страницы
?
Стандарт — UTF-8. Неправильная кодировка вызывает нечитаемые символы и мешает поисковику корректно распознать текст страницы.
Указана кодировка на странице utf-8.
Язык
en
Атрибут lang в HTML-теге
?
Атрибут lang (<html lang="ru">) сообщает поисковикам и браузерам, на каком языке написана страница. Помогает при ранжировании в региональном поиске.
Язык документа указан явно: en.
Скорость загрузки
~1,10сек
Время отклика сервера (TTFB)
?
Time To First Byte — время до получения первого байта от сервера. Норма до 200 мс. Медленный отклик ухудшает пользовательский опыт и ранжирование: Яндекс и Google учитывают скорость страниц.
Скорость загрузки сайта 1,10сек превышает 1 секунду. Желательно улучшить работу сайта!
Объем документа
67Кб
Размер HTML-кода страницы
?
Слишком большой HTML замедляет парсинг браузером и сканирование поисковым роботом. Рекомендуется не более 200 Кб.
Объем html-документа 67Кб оптимален.
Структура html-документа корректна.
Ресурсы
Ресурсы: 5
Внешние ресурсы страницы (CSS, JS, изображения)
?
Количество и тип подключённых ресурсов влияют на скорость загрузки. Большое число запросов увеличивает время рендеринга страницы.
Кол-во файлов ресурсов 5 достаточно.
Показать полный список ресурсов
| Тип | Название | Значение |
|---|---|---|
| stylesheet | https://fonts.googleapis.com/css2?family=Helvetica Neue:ital,wght@0,100;0,300;0,400;0,500;0,700;0,900;1,100;1,300;1,400;1,500;1,700;1,900&display=swap | |
| stylesheet | text/css | ../stylesheets/css/main.css |
| js | https://www.googletagmanager.com/gtag/js?id=UA-111460498-1 | |
| js | text/javascript | ../javascripts/jquery-3.2.1.min.js |
| js | text/javascript | ../javascripts/mini.js |
Серверные заголовки
Кол-во: 9
HTTP-заголовки ответа сервера
?
Заголовки сервера передают браузеру и поисковику служебную информацию: кеширование, безопасность (CSP, HSTS), сжатие (gzip). Правильная настройка ускоряет загрузку и повышает защищённость.
Найдены серверные заголовки 9шт. Подробнее про серверные заголовки.
Показать полный список серверных заголовков
| Ключ | Значение |
|---|---|
| Access-Control-Allow-Origin | * |
| Date | Sun, 23 Aug 2026 15:57:24 GMT |
| ETag | W/"10d4e-T4CfOgZWHDDBi8nIysZEefoRcyY" |
| Nel | {"report_to":"heroku-nel","response_headers":["Via"],"max_age":3600,"success_fraction":0.01,"failure_fraction":0.1} |
| Report-To | {"group":"heroku-nel","endpoints":[{"url":"https://nel.heroku.com/reports?s=QNBv1obg7%2FagQRlTRZ3WwRvOWYDtfgBSXOa%2FJcvL8RU%3D\u0026sid=67ff5de4-ad2b-4112-9289-cf96be89efed\u0026ts=1787500644"}],"max_age":3600} |
| Reporting-Endpoints | heroku-nel="https://nel.heroku.com/reports?s=QNBv1obg7%2FagQRlTRZ3WwRvOWYDtfgBSXOa%2FJcvL8RU%3D&sid=67ff5de4-ad2b-4112-9289-cf96be89efed&ts=1787500644" |
| Server | Heroku |
| Via | 1.1 heroku-router |
| X-Powered-By | Express |
CMS
Не определена
Система управления сайтом (движок)
?
CMS — это движок, на котором работает сайт (WordPress, 1C-Bitrix, Tilda и др.). Знание CMS помогает понять возможности SEO-оптимизации и подобрать подходящие инструменты. «Не определена» — вероятно, самописный сайт или нестандартная сборка.
CMS не определена. Вероятно, сайт самописный либо движок надёжно скрыт. Это не ошибка.
Веб-сервер
Node.js
Программное обеспечение сервера
?
Веб-сервер — это ПО, которое отдаёт страницы посетителям (nginx, Apache, IIS, LiteSpeed и др.). Определяется по серверным заголовкам ответа (Server, X-Powered-By и т.п.). «Не определён» — сервер намеренно скрывает эти заголовки, это нормальная практика безопасности.
Сайт работает на веб-сервере Node.js.
Мета-теги Готовность: 32%
Title
Hyeonsu B. Kang
Заголовок страницы в браузере и поисковой выдаче
?
Title — главный SEO-заголовок страницы. Влияет на CTR в поиске и ранжирование. Оптимальная длина: 50–70 символов. Ключевые слова — ближе к началу.
Необходимо увеличить число символов в title (текущее значение мало: 15, минимум: 25, оптимально: от 40 до 45)
Дублей словоформ в title не найдено.
Description
Описание страницы в поисковой выдаче (сниппет)
?
Meta Description — текст под заголовком в выдаче. Напрямую на позиции не влияет, но влияет на CTR. Оптимальная длина: 120–160 символов.
Установите мета-тег description!
Keywords
Список ключевых слов страницы (устаревший тег)
?
Meta Keywords не учитывается Яндексом и Google для ранжирования с 2009–2012 годов. Заполнение не обязательно, но не вредит. Конкурент может использовать содержимое для анализа.
Установите мета-тег keywords!
Канонический Url
Указывает поисковику основную версию страницы
?
Canonical (rel=canonical) предотвращает проблему дублей страниц. Должен точно совпадать с URL проверяемой страницы. Неправильный canonical может передать ссылочный вес на другую страницу.
Рекомендуем прописать канонический Url.
Robots
Ошибок нет
Директивы для поисковых роботов на уровне страницы
?
Meta Robots управляет индексацией конкретной страницы: index/noindex — индексировать ли, follow/nofollow — следовать ли по ссылкам. Noindex полностью исключает страницу из поиска.
Meta-тег robots не указан. Страница свободна для индексации.
Адаптивность
width=device-width, initial-scale=1, shrink-to-fit=no
Настройка масштабирования на мобильных устройствах
?
Тег viewport (<meta name="viewport">) сообщает браузеру, как масштабировать страницу на мобильных. Стандарт: width=device-width, initial-scale=1. Отсутствие — признак отсутствия мобильной версии.
Meta-тег viewport со значением-константой width=device-width задаёт ширину страницы в соответствии с размером экрана.
Meta-тег viewport со значением initial-scale=1.0 определяет масштаб 1:1, т.е. «не масштабировать».
Разметка OpenGraph
Не найдено
Мета-теги для красивых превью в соцсетях
?
OpenGraph (og:title, og:description, og:image) управляет тем, как страница выглядит при репосте в социальных сетях и мессенджерах. Отсутствие OG-тегов — невзрачный превью при шеринге.
Разметка OpenGraph не задана. Страница не оптимизирована под социальные сети. Мета-теги с разметкой Og помогают социальным роботам лучше структурировать Ваш сайт.
Все мета-теги
Кол-во: 2
Полный список мета-тегов страницы
?
Таблица всех meta-тегов, включая нестандартные. Позволяет найти опечатки, дубли и лишние теги.
Найдены мета-теги 2шт. Мета-теги не видимы для человека и предназначены для обмена информацией между веб-страницей и поисковыми системами, браузерами и другими веб-службами. С ними роботы 🤖 и устройства ведут себя более ожидаемо.
Показать полный список мета-тегов
| Тип | Название | Значение |
|---|---|---|
| name | viewport | width=device-width, initial-scale=1.0 |
| name | viewport | width=device-width, initial-scale=1, shrink-to-fit=no |
Оптимизация Готовность: 25%
Структура
Ошибок нет
Семантические HTML-элементы страницы
?
Проверяет наличие основных структурных элементов: nav, header, footer, main. Корректная семантическая структура помогает поисковику понять архитектуру страницы.
Структура документа корректна (теги <html> и <body> присутствуют по одному на документ).
Контент
Есть ошибки
Объём и качество текстового содержимого
?
Анализирует объём полезного текста на странице. Слишком мало — страница может считаться малополезной. Слишком много — ухудшается читаемость и восприятие.
Абзацев с текстом 2 слишком мало. Добавьте больше абзацев с текстом (тег <p>)!
Слова из title 3 встречаются в тексте достаточно.
Среднее число слов в абзаце 195 достаточно.
Кол-во знаков контента 26488 на странице оптимально.
Кол-во слов 3871 на странице оптимально.
Заголовки
Есть ошибки
Иерархия заголовков H1–H6
?
H1 должен быть один и содержать ключевой запрос. H2–H6 описывают подразделы. Пропуск уровней (H1 → H3) и несколько H1 — типичные ошибки, снижающие понятность страницы для поисковика.
Не обнаружено заголовков на странице. Добавьте заголовки (<h1>, <h2> или <h3>)
Тошнота
5,57
Насколько одно слово доминирует в тексте
?
Классическая тошнота = √(частота самого повторяющегося слова). Норма до 7–8: текст воспринимается естественно. Выше — поисковик может счесть страницу переспамленной.
Тошнота превышает норму 5. Измените текст страницы!
Академич. тошнота
32,47%
Насколько текст перенасыщен ключевыми словами
?
Академическая тошнота = (частота слова / общее количество слов) × 100%. Показывает долю конкретного слова в тексте. Норма 5–15%.
Академическая тошнота превышает норму 5-15%. Измените текст страницы!
Семантическое ядро
20
Наиболее часто встречающиеся слова на странице
?
Топ слов по частоте использования. Показывает, какие слова доминируют в тексте с точки зрения поисковика.
Контент страницы содержит осмысленный текст и слова.
Показать список слов
| Слово | Кол-во | Частота |
|---|---|---|
| papers | 31 | 0,80% |
| research | 30 | 0,77% |
| hyeonsu | 20 | 0,52% |
| system | 16 | 0,41% |
| scholars | 16 | 0,41% |
| relevant | 15 | 0,39% |
| systems | 14 | 0,36% |
| scientific | 13 | 0,34% |
| design | 13 | 0,34% |
| reading | 12 | 0,31% |
| bibtex | 12 | 0,31% |
| threads | 12 | 0,31% |
| endnote | 11 | 0,28% |
| scholarly | 11 | 0,28% |
| biospark | 10 | 0,26% |
| interaction | 9 | 0,23% |
| through | 9 | 0,23% |
| aniket | 9 | 0,23% |
| kittur | 9 | 0,23% |
| approaches | 9 | 0,23% |
Индексация Готовность: 30%
Индексирование
Ошибок нет
Разрешено ли индексирование страницы
?
Проверяет, не закрыта ли страница от индексации через robots.txt, meta robots или X-Robots-Tag. Страница, закрытая от индексации, не появится в поисковой выдаче.
Анкоров на странице 64 оптимально. Поисковые роботы обязательно проиндексируют сайт.
Robots.txt
Найден корректный robots.txt
Файл управления сканированием сайта роботами
?
Robots.txt указывает поисковым роботам, какие страницы сканировать, а какие — нет. Ошибки в файле могут случайно закрыть важные разделы от индексации.
Robots.txt настроен корректно. Размер файла: 68870 байт. Загружен за: 1сек.
Проверяемая страница не запрещена в robots.txt.
Robots.txt доступен по постоянному адресу
Цепочка редиректов для файла robots.txt:
http://hyeonsukang.com/robots.txt
302 Found
http://www.hyeonsukang.com/
200 OK
Показать содержимое robots.txt
<!DOCTYPE html>
<html lang="en">
<head>
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=UA-111460498-1"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'UA-111460498-1');
</script>
<title>Hyeonsu B. Kang</title>
<!-- Required meta tags -->
<meta name="viewport" content="width=device-width, initial-scale=1.0" charset="utf-8">
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link href="https://fonts.googleapis.com/css2?family=Helvetica Neue:ital,wght@0,100;0,300;0,400;0,500;0,700;0,900;1,100;1,300;1,400;1,500;1,700;1,900&display=swap" rel="stylesheet">
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
<link rel="shortcut icon" href="../images/favicon.ico">
<link rel="stylesheet" href="../stylesheets/css/main.css" media="screen" type="text/css">
<script src="../javascripts/jquery-3.2.1.min.js" type="text/javascript" charset="utf-8"></script>
<script src="../javascripts/mini.js" type="text/javascript" charset="utf-8"></script>
</head>
<body>
<div class="sidebar">
<div class="author-avatar">
<img src="images/hyeonsu_profile.png" alt="A profile picture of Hyeonsu Kang"/>
</div>
<ul>
<li>
<span class="fake-link" onclick="console.log(this.childNodes); this.childNodes[4].outerText = ['hyeonsuk','@','cs','.','cmu','.','edu'].join(''); this.style.cursor = 'text';">
<svg class="valign svg-inline--fa fa-envelope-square fa-w-14 fa-fw" aria-hidden="true" data-prefix="fas" data-icon="envelope-square" role="img" xmlns="http://www.w3.org/2000/svg" width='16px' viewBox="0 0 448 512" data-fa-i2svg=""><path fill="currentColor" d="M400 32H48C21.49 32 0 53.49 0 80v352c0 26.51 21.49 48 48 48h352c26.51 0 48-21.49 48-48V80c0-26.51-21.49-48-48-48zM178.117 262.104C87.429 196.287 88.353 196.121 64 177.167V152c0-13.255 10.745-24 24-24h272c13.255 0 24 10.745 24 24v25.167c-24.371 18.969-23.434 19.124-114.117 84.938-10.5 7.655-31.392 26.12-45.883 25.894-14.503.218-35.367-18.227-45.883-25.895zM384 217.775V360c0 13.255-10.745 24-24 24H88c-13.255 0-24-10.745-24-24V217.775c13.958 10.794 33.329 25.236 95.303 70.214 14.162 10.341 37.975 32.145 64.694 32.01 26.887.134 51.037-22.041 64.72-32.025 61.958-44.965 81.325-59.406 95.283-70.199z"></path></svg><!-- <i class="fas fa-fw fa-envelope-square" aria-hidden="true"></i> -->
<span class='valign link'>Email</span>
</span>
</li>
<li>
<svg class="valign svg-inline--fa fa-file-alt fa-w-12 fa-fw" aria-hidden="true" data-prefix="fas" data-icon="file-alt" role="img" xmlns="http://www.w3.org/2000/svg" width='16px' height='16px' viewBox="0 0 384 512" data-fa-i2svg=""><path fill="currentColor" d="M224 136V0H24C10.7 0 0 10.7 0 24v464c0 13.3 10.7 24 24 24h336c13.3 0 24-10.7 24-24V160H248c-13.2 0-24-10.8-24-24zm64 236c0 6.6-5.4 12-12 12H108c-6.6 0-12-5.4-12-12v-8c0-6.6 5.4-12 12-12h168c6.6 0 12 5.4 12 12v8zm0-64c0 6.6-5.4 12-12 12H108c-6.6 0-12-5.4-12-12v-8c0-6.6 5.4-12 12-12h168c6.6 0 12 5.4 12 12v8zm0-72v8c0 6.6-5.4 12-12 12H108c-6.6 0-12-5.4-12-12v-8c0-6.6 5.4-12 12-12h168c6.6 0 12 5.4 12 12zm96-114.1v6.1H256V0h6.1c6.4 0 12.5 2.5 17 7l97.9 98c4.5 4.5 7 10.6 7 16.9z"></path></svg>
<a class="valign link" href="files/cv-hyeonsu-kang.pdf" target="_blank">CV</a>
</li>
<li>
<svg class="valign" xmlns="http://www.w3.org/2000/svg" aria-label="Google Scholar" role="img" viewBox="0 0 512 512" width="16px"><rect width="512" height="512" rx="15%" fill="#4285f4"/><path fill="#ffffff" d="M213 111l-107 94h69c5 45 41 64 78 67-7 18-4 27 7 39-43 1-103 26-103 67 4 45 63 54 92 54 38 1 81-19 90-54 4-35-10-54-31-71-23-18-28-28-21-40 15-17 35-27 39-51 2-17-2-28-6-43l45-38-1 16c-3 2-5 6-5 9v103c2 13 22 11 23 0V160c0-3-2-7-5-8v-25l16-16zm58 141c-61 10-87-87-38-99 56-11 83 86 38 99zm-5 73c60 13 61 63 10 78-44 9-82-4-81-30 0-25 35-48 71-48z"/></svg>
<a class="valign link" href="https://scholar.google.com/citations?hl=en&user=NBcNOCAAAAAJ&view_op=list_works&sortby=pubdate" target="_blank">Google Scholar</a>
</li>
<li>
<svg class="valign" version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" width="16px" viewBox="0 0 512 512" enable-background="new 0 0 512 512" xml:space="preserve"><g id="Layer_1_1_" display="none"><g display="inline"><g><defs><rect id="SVGID_1_" width="512" height="512"/></defs><clipPath id="SVGID_2_"><use xlink:href="#SVGID_1_" overflow="visible"/></clipPath><g clip-path="url(#SVGID_2_)"><rect x="439" opacity="0.4" fill="#FF5050" enable-background="new " width="73" height="512"/><rect opacity="0.4" fill="#FF5050" enable-background="new " width="73" height="512"/><rect x="73" opacity="0.1" fill="#FF5050" enable-background="new " width="73" height="512"/><rect y="73" opacity="0.1" fill="#FF5050" enable-background="new " width="512" height="73"/><rect x="366" opacity="0.1" fill="#FF5050" enable-background="new " width="73" height="512"/><rect y="366" opacity="0.1" fill="#FF5050" enable-background="new " width="512" height="73"/><rect x="-0.5" opacity="0.4" fill="#FF5050" enable-background="new " width="512" height="73"/><rect y="439" opacity="0.4" fill="#FF5050" enable-background="new " width="512" height="73"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M73,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M146,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M219,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M292,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M366,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M439,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,73H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,146H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,219H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,292H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,366H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,439H0"/></g></g></g></g><g><path fill-rule="evenodd" clip-rule="evenodd" fill="#006C92" d="M222.923,309.248c-5.141-3.959-9.421-7.254-14.124-10.875c-1.103-58.089-16.891-111.251-55.917-157.233c61.353,0,121.45,0,181.639,0c8.162,9.502,23.666,73.725,18.906,81.552c-0.888-2.451-1.695-4.305-2.234-6.233c-3.313-11.861-6.621-23.725-9.807-35.621c-1.041-3.887-3.247-6.387-7.069-7.663c-7.012-2.342-12.401-6.859-17.142-12.464c-1.527-1.806-4.29-3.642-6.488-3.643c-29.977-0.008-59.953,0.302-89.93,0.547c-0.488,0.004-0.976,0.179-1.993,0.376c-3.875,6.521-8.881,12.428-17.626,14.631c1.321,4.321,2.249,8.162,3.653,11.819c8.396,21.86,14.439,44.303,17.03,67.615C223.883,270.6,225.331,289.162,222.923,309.248z"/><linearGradient id="SVGID_3_" gradientUnits="userSpaceOnUse" x1="163.1348" y1="291.5703" x2="414.8418" y2="291.5703"><stop offset="0" style="stop-color:#FFB000"/><stop offset="0.1148" style="stop-color:#FFB80A"/><stop offset="0.3091" style="stop-color:#FFCE25"/><stop offset="0.5" style="stop-color:#FFE945"/><stop offset="0.5753" style="stop-color:#FFDF39"/><stop offset="0.8555" style="stop-color:#FFBD10"/><stop offset="1" style="stop-color:#FFB000"/></linearGradient><path fill-rule="evenodd" clip-rule="evenodd" fill="url(#SVGID_3_)" d="M206.025,310.986c5.009,4.051,10.467,7.543,16.324,11.723c58.528-47.25,122.667-83.806,192.493-110.428c-72.316,42.427-141.951,87.977-192.027,158.579c-1.744-2.23-2.826-3.391-3.654-4.709c-18.072-28.77-36.124-57.555-54.142-86.359c-0.775-1.238-0.791-1.689-1.885-4.064C163.135,275.727,191.654,299.367,206.025,310.986z"/><path fill-rule="evenodd" clip-rule="evenodd" fill="#0078A7" d="M122.477,161.298c10.53,0,19.721,0,29.948,0c24.454,39.334,43.856,81.225,45.772,129.499C183.256,242.115,157.08,200.002,122.477,161.298z"/><path fill-rule="evenodd" clip-rule="evenodd" fill="#2DA2DC" d="M100.556,194.834c9.749-0.458,19.497-0.917,29.588-1.392c23.583,26.636,45.464,53.979,53.751,89.6c-21.158-35.559-52.112-61.667-83.85-87.028c-0.295-0.332-1.175-1.117-1.175-1.117S100.036,194.835,100.556,194.834z"/><path fill-rule="evenodd" clip-rule="evenodd" d="M163.288,275.686c0,0-0.042,0.041-0.042,0.041L163.288,275.686z"/></g></svg>
<a class="valign link" href="https://www.semanticscholar.org/author/Hyeonsu-Kang/26997666" target="_blank">Semantic Scholar</a>
</li>
</ul>
</div>
<div class="mobile-avatar">
<div class="center-flex">
<div class="author-avatar mobile">
<img src="images/hyeonsu_profile.png" alt="A profile picture of Hyeonsu Kang"/>
</div>
<div>
<ul class="no-margin">
<li>
<span class="fake-link" onclick="console.log(this.childNodes); this.childNodes[4].outerText = ['hyeonsuk','@','cs','.','cmu','.','edu'].join(''); this.style.cursor = 'text';">
<svg class="valign svg-inline--fa fa-envelope-square fa-w-14 fa-fw" aria-hidden="true" data-prefix="fas" data-icon="envelope-square" role="img" xmlns="http://www.w3.org/2000/svg" width='16px' viewBox="0 0 448 512" data-fa-i2svg=""><path fill="currentColor" d="M400 32H48C21.49 32 0 53.49 0 80v352c0 26.51 21.49 48 48 48h352c26.51 0 48-21.49 48-48V80c0-26.51-21.49-48-48-48zM178.117 262.104C87.429 196.287 88.353 196.121 64 177.167V152c0-13.255 10.745-24 24-24h272c13.255 0 24 10.745 24 24v25.167c-24.371 18.969-23.434 19.124-114.117 84.938-10.5 7.655-31.392 26.12-45.883 25.894-14.503.218-35.367-18.227-45.883-25.895zM384 217.775V360c0 13.255-10.745 24-24 24H88c-13.255 0-24-10.745-24-24V217.775c13.958 10.794 33.329 25.236 95.303 70.214 14.162 10.341 37.975 32.145 64.694 32.01 26.887.134 51.037-22.041 64.72-32.025 61.958-44.965 81.325-59.406 95.283-70.199z"></path></svg><!-- <i class="fas fa-fw fa-envelope-square" aria-hidden="true"></i> -->
<span class='valign link'>Email</span>
</span>
</li>
<li>
<svg class="valign svg-inline--fa fa-file-alt fa-w-12 fa-fw" aria-hidden="true" data-prefix="fas" data-icon="file-alt" role="img" xmlns="http://www.w3.org/2000/svg" width='16px' height='16px' viewBox="0 0 384 512" data-fa-i2svg=""><path fill="currentColor" d="M224 136V0H24C10.7 0 0 10.7 0 24v464c0 13.3 10.7 24 24 24h336c13.3 0 24-10.7 24-24V160H248c-13.2 0-24-10.8-24-24zm64 236c0 6.6-5.4 12-12 12H108c-6.6 0-12-5.4-12-12v-8c0-6.6 5.4-12 12-12h168c6.6 0 12 5.4 12 12v8zm0-64c0 6.6-5.4 12-12 12H108c-6.6 0-12-5.4-12-12v-8c0-6.6 5.4-12 12-12h168c6.6 0 12 5.4 12 12v8zm0-72v8c0 6.6-5.4 12-12 12H108c-6.6 0-12-5.4-12-12v-8c0-6.6 5.4-12 12-12h168c6.6 0 12 5.4 12 12zm96-114.1v6.1H256V0h6.1c6.4 0 12.5 2.5 17 7l97.9 98c4.5 4.5 7 10.6 7 16.9z"></path></svg>
<a class="valign link" href="files/cv-hyeonsu-kang.pdf" target="_blank">CV</a>
</li>
<li>
<svg class="valign" xmlns="http://www.w3.org/2000/svg" aria-label="Google Scholar" role="img" viewBox="0 0 512 512" width="16px"><rect width="512" height="512" rx="15%" fill="#4285f4"/><path fill="#ffffff" d="M213 111l-107 94h69c5 45 41 64 78 67-7 18-4 27 7 39-43 1-103 26-103 67 4 45 63 54 92 54 38 1 81-19 90-54 4-35-10-54-31-71-23-18-28-28-21-40 15-17 35-27 39-51 2-17-2-28-6-43l45-38-1 16c-3 2-5 6-5 9v103c2 13 22 11 23 0V160c0-3-2-7-5-8v-25l16-16zm58 141c-61 10-87-87-38-99 56-11 83 86 38 99zm-5 73c60 13 61 63 10 78-44 9-82-4-81-30 0-25 35-48 71-48z"/></svg>
<a class="valign link" href="https://scholar.google.com/citations?hl=en&user=NBcNOCAAAAAJ&view_op=list_works&sortby=pubdate" target="_blank">Google Scholar</a>
</li>
<li>
<svg class="valign" version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" width="16px" viewBox="0 0 512 512" enable-background="new 0 0 512 512" xml:space="preserve"><g id="Layer_1_1_" display="none"><g display="inline"><g><defs><rect id="SVGID_1_" width="512" height="512"/></defs><clipPath id="SVGID_2_"><use xlink:href="#SVGID_1_" overflow="visible"/></clipPath><g clip-path="url(#SVGID_2_)"><rect x="439" opacity="0.4" fill="#FF5050" enable-background="new " width="73" height="512"/><rect opacity="0.4" fill="#FF5050" enable-background="new " width="73" height="512"/><rect x="73" opacity="0.1" fill="#FF5050" enable-background="new " width="73" height="512"/><rect y="73" opacity="0.1" fill="#FF5050" enable-background="new " width="512" height="73"/><rect x="366" opacity="0.1" fill="#FF5050" enable-background="new " width="73" height="512"/><rect y="366" opacity="0.1" fill="#FF5050" enable-background="new " width="512" height="73"/><rect x="-0.5" opacity="0.4" fill="#FF5050" enable-background="new " width="512" height="73"/><rect y="439" opacity="0.4" fill="#FF5050" enable-background="new " width="512" height="73"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M73,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M146,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M219,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M292,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M366,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M439,0v512"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,73H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,146H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,219H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,292H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,366H0"/><path fill="none" stroke="#FF4D4D" stroke-width="0.25" d="M512,439H0"/></g></g></g></g><g><path fill-rule="evenodd" clip-rule="evenodd" fill="#006C92" d="M222.923,309.248c-5.141-3.959-9.421-7.254-14.124-10.875c-1.103-58.089-16.891-111.251-55.917-157.233c61.353,0,121.45,0,181.639,0c8.162,9.502,23.666,73.725,18.906,81.552c-0.888-2.451-1.695-4.305-2.234-6.233c-3.313-11.861-6.621-23.725-9.807-35.621c-1.041-3.887-3.247-6.387-7.069-7.663c-7.012-2.342-12.401-6.859-17.142-12.464c-1.527-1.806-4.29-3.642-6.488-3.643c-29.977-0.008-59.953,0.302-89.93,0.547c-0.488,0.004-0.976,0.179-1.993,0.376c-3.875,6.521-8.881,12.428-17.626,14.631c1.321,4.321,2.249,8.162,3.653,11.819c8.396,21.86,14.439,44.303,17.03,67.615C223.883,270.6,225.331,289.162,222.923,309.248z"/><linearGradient id="SVGID_3_" gradientUnits="userSpaceOnUse" x1="163.1348" y1="291.5703" x2="414.8418" y2="291.5703"><stop offset="0" style="stop-color:#FFB000"/><stop offset="0.1148" style="stop-color:#FFB80A"/><stop offset="0.3091" style="stop-color:#FFCE25"/><stop offset="0.5" style="stop-color:#FFE945"/><stop offset="0.5753" style="stop-color:#FFDF39"/><stop offset="0.8555" style="stop-color:#FFBD10"/><stop offset="1" style="stop-color:#FFB000"/></linearGradient><path fill-rule="evenodd" clip-rule="evenodd" fill="url(#SVGID_3_)" d="M206.025,310.986c5.009,4.051,10.467,7.543,16.324,11.723c58.528-47.25,122.667-83.806,192.493-110.428c-72.316,42.427-141.951,87.977-192.027,158.579c-1.744-2.23-2.826-3.391-3.654-4.709c-18.072-28.77-36.124-57.555-54.142-86.359c-0.775-1.238-0.791-1.689-1.885-4.064C163.135,275.727,191.654,299.367,206.025,310.986z"/><path fill-rule="evenodd" clip-rule="evenodd" fill="#0078A7" d="M122.477,161.298c10.53,0,19.721,0,29.948,0c24.454,39.334,43.856,81.225,45.772,129.499C183.256,242.115,157.08,200.002,122.477,161.298z"/><path fill-rule="evenodd" clip-rule="evenodd" fill="#2DA2DC" d="M100.556,194.834c9.749-0.458,19.497-0.917,29.588-1.392c23.583,26.636,45.464,53.979,53.751,89.6c-21.158-35.559-52.112-61.667-83.85-87.028c-0.295-0.332-1.175-1.117-1.175-1.117S100.036,194.835,100.556,194.834z"/><path fill-rule="evenodd" clip-rule="evenodd" d="M163.288,275.686c0,0-0.042,0.041-0.042,0.041L163.288,275.686z"/></g></svg>
<a class="valign link" href="https://www.semanticscholar.org/author/Hyeonsu-Kang/26997666" target="_blank">Semantic Scholar</a>
</li>
</ul>
</div>
</div>
</div>
<div class="mainbody">
<div class="container">
<span class="first-name">Hyeonsu</span><span class="last-name">B. Kang</span>
<div class="banner-left-aligned">
<span class="news">[News!]</span> <a class="link" href="files/KANG2025-BioSpark.pdf" target="_blank">BioSpark</a> was featured in a <em>Washington Post</em> article by David Ovalle titled <em>“Is AI rewiring our minds? Scientists probe cognitive cost of chatbots.”</em> The article explores the nuanced research behind viral claims that AI is making us lazier or less intelligent. Read it here: <a href="https://www.washingtonpost.com/health/2025/06/29/chatgpt-ai-brain-impact/" target="_blank">washingtonpost.com</a>.
<br/>
<span class="news">[News!]</span> I started as a Senior Applied Scientist at Microsoft! (<a href="https://www.microsoft.com/en-us/research/people/hyeonsukang/">Link</a>)
<br/>
<span class="news">[News!]</span> <a class="link" href="files/KANG2025-BioSpark.pdf" target="_blank">BioSpark</a> was awarded a Best Paper Honorable Mention at CHI 2025!
<br/>
<span class="news">[News!]</span> <a class="link" href="https://www.csail.mit.edu/person/nouran-soliman" target="_blank">Nouran</a>'s work on meronymous interaction received a Best Paper Award at CHI 2024! <!-- 04/25/2024 -->
<br/>
<span class="news">[News!]</span> <a class="link" href="https://www.csail.mit.edu/person/nouran-soliman" target="_blank">Nouran</a>'s work on meronymous interaction was featured on <a class="link" href="https://news.mit.edu/2024/litweeture-uses-meronymity-social-media-open-discussions-0418" target="_blank">MIT News</a>!<!-- 04/18/2024 -->
</div>
<br/>
<!-- <span class='industry bio link' onclick="showBio('industry')">Industry Bio</span> |
<span class='academic bio link' onclick="showBio('academic')">Academic Bio</span> -->
<div id="industry" class="bio active">
<p class="box">
I'm a <a href="https://www.microsoft.com/en-us/research/people/hyeonsukang/">Senior Applied Scientist at Microsoft</a> in the Outlook organization, where I build and study agentic systems for email work, with an emphasis on <strong>delegation</strong> and <strong>agent's proactivity</strong>.
I hold a Ph.D. in Human-Computer Interaction from Carnegie Mellon University (CMU). My training is grounded in <strong>cognitive science and behavioral methods</strong>, with prior work on the scientific study of human-AI co-creativity and ML/LLM-powered interactive systems. Across projects, I pair empirical research (controlled experiments, mixed-method studies, behavioral measurement) with system-building to translate findings into product direction and evaluation frameworks.
Previously, I worked in PowerPoint AI on multimodal agentic systems for presentation generation/editing and slide-native evaluation.
<br/><br/>
I've collaborated with the Toyota Research Institute, the
<a class="link" href="https://allenai.org/" target="_blank">Allen Institute for AI (AI2)</a>, and MIT to design and deploy AI-driven systems with real-world
impact.
At AI2, I worked on Semantic Scholar's improved paper-alert
emails, led engagement analyses that guided their launch, and published
multiple research papers with AI2 collaborators.
Additionally, I partnered
with <a class="link" href="https://conservationx.com" target="_blank">
Conservation X Labs
</a> to develop team-formation algorithms for global open-innovation
contests offering over $2 million in prize funding.
<br/><br/>
My research is now required reading at Virginia Tech and CMU. I've received multiple awards, including a Best Paper Award at ACM CHI (2024), a Best Paper Honorable Mention Award at ACM CHI (2025), and a Google Cloud Innovator Award (2021).
</p>
</div>
<!--
<div id="academic" class="bio">
<p class="box">
Hyeonsu Kang (Ph.D., Carnegie Mellon University) is a Human-AI Interaction researcher specializing in enhancing cognitive efficiency and creativity through collaborative AI systems.
His work combines cognitive theories with cutting-edge AI to improve problem-solving and ideation for both experts and novices across various domains.
Kang's research spans three key areas:
<ul class="box-tight">
<li>1. Enhancing outside-the-box thinking for domain experts and novices
[<a class="link" href="http://www.hyeonsukang.com/files/KANG2022-tochi-augmenting.pdf" target="_blank">TOCHI'22</a>,
<a class="link" href="http://www.hyeonsukang.com/files/HOPE2022-Scaling.pdf" target="_blank">CHI'22</a>,
<a class="link" href="http://www.hyeonsukang.com/files/KANG2022-naacl-augmenting-with-retrieval-across-domains.pdf" target="_blank">NAACL'22</a>,
<a class="link" href="https://arxiv.org/abs/2503.09838" target="_blank">CHI'25 🥇 & NeurIPS'23 & CHI'24, <a class="link" href="https://arxiv.org/pdf/2312.12681.pdf" target="_blank">AAAI'24</a>]
</li>
<li>2. Facilitating effective discovery and synthesis of relevant prior knowledge
[<a class="link" href="http://www.hyeonsukang.com/files/KANG2023-Synergi.pdf" target="_blank">UIST'23</a>,
<a class="link" href="http://www.hyeonsukang.com/files/KANG2023-ComLittee.pdf" target="_blank">CHI'23</a>,
<a class="link" href="http://www.hyeonsukang.com/files/KANG2022-Threddy.pdf" target="_blank">UIST'22</a>,
<a class="link" href="http://www.hyeonsukang.com/files/KANG2022-from-who-you-know-to-what-you-read.pdf" target="_blank">CHI'22</a>,
<a class="link" href="https://arxiv.org/pdf/2403.02939.pdf" target="_blank">CHI'24</a>]
</li>
<li>3. Promoting social learning and idea development through augmented feedback and expertise exchange
[<a class="link" href="http://www.hyeonsukang.com/files/KANG2018-Paragon.pdf" target="_blank">CHI'18</a>,
<a class="link" href="http://www.hyeonsukang.com/files/KANG2017-Omnicode.pdf" target="_blank">UIST'17</a>,
Collective Intelligence'19, <a class="link" href="https://arxiv.org/pdf/2402.17847.pdf" target="_blank">CHI'24 🏆</a>]
</li>
</ul>
His work has resulted in real-world impacts, including improving personalized email alerts for scientific research papers (deployed at the <a class="link" href="https://allenai.org/" target="_blank">Allen Institute for Artificial Intelligence</a>) and contributing to the allocation of $2M in prize money for global conservation innovation contests (<a class="link" href="https://conservationx.com" target="_blank">Conservation X Labs</a>, a conservation-focused non-profit).
His research has fostered collaborations with professionals across various disciplines (e.g., engineers, designers, scientists, and teachers) and organizations (e.g., MIT, the University of Maryland, the University of Washington, and KAIST, and industry partners such as <a class="link" href="https://conservationx.com" target="_blank">Conservation X</a>, the <a class="link" href="https://allenai.org/" target="_blank">Allen Institute for Artificial Intelligence</a>, and the <a class="link" href="https://www.tri.global/" target="_blank">Toyota Research Institute</a>).
<br/><br/>
Kang's contributions have been recognized with a <span class="bold">best paper award</span> at ACM CHI 2024, a <span class="bold">best paper honorable mention award</span> at ACM CHI 2025, and a Google Cloud Innovator Award (2021).
His work has been published in premier NLP and HCI conferences and journals, including ACM CHI, UIST, TOCHI, AAAI, NAACL, and NeurIPS.
His research has been funded by the National Science Foundation, the Allen Institute for Artificial Intelligence, the Office of Naval Research, the Toyota Research Institute, and Google Cloud.
Prior to his Ph.D., Kang received his BS in Computer Science and Engineering at <a class="link" href="https://en.snu.ac.kr/" target="_blank">Seoul National University</a>.
He also worked and interned at MIT, the Allen Institute for AI, UC San Diego, and Tableau Software.
He was previously supported by the South Korean National Scholarship for Science and Engineering.
</p>
</div> -->
</div>
<div class="container">
<p class="header">Publications</p>
</div>
<div id="row-users-mispredict" class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/users_mispredict_arxiv.png"/>
<span class="thumbnail-tag">Pre-print</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/users_mispredict_arxiv.pdf" target="_blank">Users Mispredict Their Own Preferences for AI Writing Assistance</a>
</div>
<div class="first-few authors">
Vivian Lai, Zana Buçinca, Nil-Jana Akpinar, Mo Houtti, <span class="bold">Hyeonsu B. Kang</span>, Kevin Chian, Namjoon Suh, Alex C. Williams
</div>
<div class="venue">
<span class="chi-tag venue">ArXiv</span>
[<a class="link" href="files/users_mispredict_arxiv.pdf" target="_blank">PDF</a>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
Proactive AI writing assistants need to predict when users want drafting help, yet we lack empirical understanding of what drives preferences. Through a factorial vignette study with 50 participants making 750 pairwise comparisons, we find compositional effort dominates decisions (rho=0.597) while urgency shows no predictive power (rho≈0). More critically, users exhibit a striking perception-behavior gap: they rank urgency first in self-reports despite it being the weakest behavioral driver, representing a complete preference inversion. This misalignment has measurable consequences. Systems designed from users' stated preferences achieve only 57.7% accuracy, underperforming even naive baselines, while systems using behavioral patterns reach significantly higher 61.3% (p<0.05). These findings demonstrate that relying on user introspection for system design actively misleads optimization, with direct implications for proactive natural language generation (NLG) systems.
</div>
</div>
</div>
<div class="divider"></div>
<div id="row-vlm-slideeval" class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2025-VLM-SlideEval.png"/>
<span class="thumbnail-tag">NeurIPS 2025</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/KANG2025-VLM-SlideEval.pdf" target="_blank">VLM-SlideEval: Evaluating VLMs on Structured Comprehension and Perturbation Sensitivity in PPT</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang</span>, Emily Bao, Anjan Goswami
</div>
<div class="venue">
<span class="chi-tag venue">NeurIPS 2025 (Evaluating the Evolving LLM Lifecycle Workshop)</span>
[<a class="link" href="files/KANG2025-VLM-SlideEval.pdf" target="_blank">PDF</a>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
Vision-language models (VLMs) are increasingly used to evaluate multimodal content, including presentation slides, yet their slide-specific understanding remains underexplored despite their growing role as critics in agentic, model-forward pipelines. We introduce VLM-SlideEval, an evaluation framework that probes VLMs along three axes: (1) element-level extraction from slide images aligned to ground truth; (2) robustness to controlled perturbations in geometry, style, and text; and (3) higher-level comprehension, such as recovering a deck's narrative order from shuffled slides. Using publicly available decks from <a class="link" href="https://huggingface.co/datasets/Forceless/Zenodo10K/viewer/default/pptx" target="_blank">Zenodo</a>, we standardize ground-truth element metadata from PowerPoint XML and live renderings into a unified, verifiable schema. Empirically, VLMs underperform on pixel-accurate extraction and show non-trivial agreement, fidelity, and consistency under controlled perturbations, while performing better on single-slide content understanding; however, they do not reliably capture narrative structure across slides. These results highlight the limits of current VLMs for slide evaluation and motivate calibrated, critic-in-the-loop evaluators that drive iterative refinement and selection in agentic pipelines.
</div>
</div>
</div>
<div class="divider"></div>
<div id="row-biospark" class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2025-BioSpark2.png"/>
<span class="thumbnail-tag">🥇 CHI 2025</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/KANG2025-BioSpark.pdf" target="_blank">BioSpark: Beyond Analogical Inspiration to LLM-augmented Transfer</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang</span>, David Chuan-en Lin, Yan-Ying Chen, Matthew K. Hong, Nicholas Martelaro, Aniket Kittur
</div>
<div class="venue">
<span class="chi-tag venue">CHI 2025 (Best Paper Honorable Mention 🥇)</span>
[<a class="link" href="files/KANG2025-BioSpark.pdf" target="_blank">PDF</a>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
We present BioSpark, a system for analogical innovation designed to act as a creativity partner in reducing the cognitive effort in finding, mapping, and creatively adapting diverse inspirations. While prior approaches have focused on initial stages of finding inspirations, BioSpark uses LLMs embedded in a familiar, visual, Pinterest-like interface to go beyond inspiration to supporting users in identifying the key solution mechanisms, transferring them to the problem domain, considering tradeoffs, and elaborating on details and characteristics. To accomplish this BioSpark introduces several novel contributions, including a tree-of-life enabled approach for generating relevant and diverse inspirations, as well as AI-powered cards including 'Sparks' for analogical transfer; 'Trade-offs' for considering pros and cons; and 'Q&A' for deeper elaboration. We evaluated BioSpark through workshops with professional designers and a controlled user study, finding that using BioSpark led to a greater number of generated ideas; those ideas being rated higher in creative quality; and more diversity in terms of biological inspirations used than a control condition. Our results suggest new avenues for creativity support tools embedding AI in familiar interaction paradigms for designer workflows.
</div>
</div>
</div>
<div class="divider"></div>
<div id="row-litweeture" class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/SOLIMAN2024-LITWEETURE.png"/>
<span class="thumbnail-tag">🏆 CHI 2024</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="https://dl.acm.org/doi/pdf/10.1145/3613904.3642241" target="_blank">Mitigating Barriers to Public Social Interaction with Meronymous Communication</a>
</div>
<div class="first-few authors">
Nouran Soliman, <span class="bold">Hyeonsu B. Kang</span>, Matthew Latzke, Jonathan Bragg, Joseph Chee Chang, Amy X. Zhang, David R Karger
</div>
<div class="venue">
<span class="chi-tag venue">CHI 2024 (Best Paper Award 🏆)</span>
<br/>
[<a class="link" href="https://dl.acm.org/doi/pdf/10.1145/3613904.3642241" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/full/10.1145/3613904.3642241" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="chi2024-meronimity-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="chi2024-meronimity-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="chi2024-meronimity-endnote" class="link">EndNote</span>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
In communities with social hierarchies, fear of judgment can discourage communication. While anonymity may alleviate some social pressure, fully anonymous spaces enable toxic behavior and hide the social context that motivates people to participate and helps them tailor their communication. We explore a design space of <i>meronymous communication</i>, where people can reveal carefully chosen <i>aspects</i> of their identity and also leverage trusted <i>endorsers</i> to gain credibility. We implemented these ideas in a system for scholars to meronymously seek and receive paper recommendations on Twitter and Mastodon. A formative study with 20 scholars confirmed that scholars see benefits to participating but are deterred due to social anxiety. From a month-long public deployment, we found that with meronymity, junior scholars could comfortably ask "newbie" questions and get responses from senior scholars who they normally found intimidating. Responses were also tailored to the aspects about themselves that junior scholars chose to reveal.
</div>
</div>
</div>
<div class="divider"></div>
<div id="row-paperweaver" class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/LEE2024-PAPERWEAVER.png"/>
<span class="thumbnail-tag">CHI 2024</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="https://dl.acm.org/doi/pdf/10.1145/3613904.3642196" target="_blank">PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers</a>
</div>
<div class="first-few authors">
Yoonjoo Lee, <span class="bold">Hyeonsu B. Kang</span>, Matthew Latzke, Juho Kim, Jonathan Bragg, Joseph Chee Chang, Pao Siangliulue
</div>
<div class="venue">
<span class="chi-tag venue">CHI 2024</span>
[<a class="link" href="https://dl.acm.org/doi/pdf/10.1145/3613904.3642196" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/full/10.1145/3613904.3642196" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="chi2024-paperweaver-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="chi2024-paperweaver-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="chi2024-paperweaver-endnote" class="link">EndNote</span>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
With the rapid growth of scholarly archives, researchers subscribe to "paper alert" systems that periodically provide them with recommendations of recently published papers that are similar to previously collected papers. However, researchers sometimes struggle to make sense of nuanced connections between recommended papers and their own research context, as existing systems only present paper titles and abstracts. To help researchers spot these connections, we present PaperWeaver, an enriched paper alerts system that provides contextualized text descriptions of recommended papers based on user-collected papers. PaperWeaver employs a computational method based on Large Language Models (LLMs) to infer users' research interests from their collected papers, extract context-specific aspects of papers, and compare recommended and collected papers on these aspects. Our user study (N=15) showed that participants using PaperWeaver were able to better understand the relevance of recommended papers and triage them more confidently when compared to a baseline that presented the related work sections from recommended papers.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/LO2023_CACM.png" alt="The first page of the paper PDF."/>
<span class="thumbnail-tag">CACM 2024</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="https://dl.acm.org/doi/pdf/10.1145/3659096" target="_blank">The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces</a>
</div>
<div class="first-few authors">
Kyle Lo, Joseph C. Chang, Andrew Head et al. (including <span class="bold">Hyeonsu B. Kang</span>)
</div>
<div class="venue">
<span class="ci-tag venue">Communications of the ACM (2024)</span>
<br/>
[<a class="link" href="https://dl.acm.org/doi/pdf/10.1145/3659096" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/full/10.1145/3659096" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="cacm-semantic-reader-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="cacm-semantic-reader-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="cacm-semantic-reader-endnote" class="link">EndNote</span>]
</div>
<div class="border-dashed last">
Scholarly publications are key to the transfer of knowledge from scholars to others. However, research papers are information-dense, and as the volume of the scientific literature grows, the greater the need for new technology to support scholars. In contrast to the process of finding papers, which has been transformed by Internet technology, the experience of reading research papers has changed little in decades. For instance, the PDF format for sharing papers remains widely used due to its portability but has significant downsides, inter alia, static content and poor accessibility for low-vision readers. This paper explores the question "Can recent advances in AI and HCI power intelligent, interactive, and accessible reading interfaces - even for legacy PDFs?" We describe the Semantic Reader Project, a collaborative effort across multiple institutions to explore automatic creation of dynamic reading interfaces for research papers. Through this project, we've developed a collection of novel reading interfaces and evaluated them with study participants and real-world users to show improved reading experiences for scholars. We've also released a production research paper reading interface that will continuously incorporate novel features from our research as they mature. We structure this paper around five key opportunities for AI assistance in scholarly reading - discovery, efficiency, comprehension, synthesis, and accessibility - and present an overview of our progress and discuss remaining open challenges. Augmenting scholarly documents through AI-powered interactive reading interfaces.
</div>
</div>
</div>
<div class="divider"></div>
<div id="row-synergi" class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2023-SYNERGI.png"/>
<span class="thumbnail-tag">UIST 2023</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/KANG2023-Synergi.pdf" target="_blank">Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang</span>, Sherry Tongshuang Wu, Joseph Chee Chang, Aniket Kittur
</div>
<div class="venue">
<span class="chi-tag venue">UIST 2023</span>
[<a class="link" href="files/KANG2023-Synergi.pdf" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/abs/10.1145/3586183.3606759" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="uist2023-synergi-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="uist2023-synergi-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="uist2023-synergi-endnote" class="link">EndNote</span>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
Efficiently reviewing scholarly literature and synthesizing prior art are crucial for scientific progress.
Yet, the growing scale of publications and the burden of knowledge make synthesis of research threads more challenging than ever.
While significant research has been devoted to helping scholars interact with individual papers, building research threads scattered across multiple papers remains a challenge.
Most top-down synthesis (and LLMs) make it difficult to personalize and iterate on the output, while bottom-up synthesis is costly in time and effort.
Here, we explore a new design space of mixed-initiative workflows.
In doing so we develop a novel computational pipeline, Synergi, that ties together user input of relevant seed threads with citation graphs and LLMs, to expand and structure them, respectively.
Synergi allows scholars to start with an entire threads-and-subthreads structure generated from papers relevant to their interests, and to iterate and customize on it as they wish.
In our evaluation, we find that Synergi helps scholars efficiently make sense of relevant threads, broaden their perspectives, and increases their curiosity.
We discuss future design implications for thread-based, mixed-initiative scholarly synthesis support tools.
<br/><br/>
A demo video of Synergi is available <a href="https://drive.google.com/file/d/1HVj0KGlI7maCJBc--rs5cBwJRXNfSt74/view?usp=sharing" target="_blank"><span class="link">here</span></a>.
</div>
</div>
</div>
<div class="divider"></div>
<div id="row-comlittee" class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2023-ComLittee.png"/>
<span class="thumbnail-tag">CHI 2023</span>
</div>
<div class="flex-column">
<div class="first-few">
<!-- <a class="link" href="" target="">ComLittee: Literature Discovery with Personal Elected Author Committees</a> -->
<a class="link" href="files/KANG2023-ComLittee.pdf" target="_blank">ComLittee: Literature Discovery with Personal Elected Author Committees</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang</span>, Nouran Soliman, Matt Latzke, Joseph Chee Chang, Jonathan Bragg
</div>
<div class="venue">
<span class="chi-tag venue">CHI 2023</span>
[<a class="link" href="files/KANG2023-ComLittee.pdf" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/10.1145/3544548.3581371" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="chi2023-comlittee-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="chi2023-comlittee-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="chi2023-comlittee-endnote" class="link">EndNote</span>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
In order to help scholars understand and follow a research topic, significant research has been devoted to creating systems that help scholars discover relevant papers and authors. Recent approaches have shown the usefulness of highlighting relevant authors while scholars engage in paper discovery. However, these systems do not capture and utilize users’ evolving knowledge of authors. We reflect on the design space and introduce ComLittee, a literature discovery system that supports author-centric exploration. In contrast to paper-centric interaction in prior systems, ComLittee’s author-centric interaction supports curation of research threads from individual authors, finding new authors and papers with combined signals from a paper recommender and the curated authors’ authorship graphs, and understanding them in the context of those signals. In a within-subjects experiment that compares to an author-highlighting approach, we demonstrate how ComLittee leads to a higher efficiency, quality, and novelty in author discovery that also improves paper discovery.
<br/><br/>
A demo video of ComLittee is available <a href="https://drive.google.com/file/d/1V_1Bx1ogz9g_VtgCrUCBxzSORMWHQxtk/view?usp=sharing" target="_blank"><span class="link">here</span></a>.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2022AUGMENTING_ANALOGICAL_INSPIRATION.png" alt="a purpose query 'Facilitate heat transfer in semiconductors' is shown to match to two different papers with diverse mechanisms that inspired a user study participant to come up with creative adaptation and direct application ideas"/>
<span class="thumbnail-tag">TOCHI 2022</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/KANG2022-tochi-augmenting.pdf" target="_blank">Augmenting Scientific Creativity with an Analogical Search Engine</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang</span>, Xin Qian, Tom Hope, Dafna Shahaf, Joel Chan, and Aniket Kittur
</div>
<div class="venue">
<span class="tochi-tag venue">TOCHI 2022</span>
[<a class="link" href="files/KANG2022-tochi-augmenting.pdf" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://github.com/hyeonsuukang/tochi22_dataset" target="_blank">Dataset</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/10.1145/3530013" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="tochi2022-augmenting-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="tochi2022-augmenting-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="tochi2022-augmenting-endnote" class="link">EndNote</span>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
Analogies have been central to creative problem-solving throughout the history of science and technology. As the number of scientific papers continues to increase exponentially, there is a growing opportunity for finding diverse solutions to existing problems. However, realizing this potential requires the development of a means for searching through a large corpus that goes beyond surface matches and simple keywords. Here we contribute the first end-to-end system for analogical search on scientific papers and evaluate its effectiveness with scientists' own problems. Using a human-in-the-loop AI system as a probe we find that our system facilitates creative ideation, and that ideation success is mediated by an intermediate level of matching on the problem abstraction (i.e., high versus low). We also demonstrate a fully automated AI search engine that achieves a similar accuracy with the human-in-the-loop system. We conclude with design implications for enabling automated analogical inspiration engines to accelerate scientific innovation.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2022-Threddy.png"/>
<span class="thumbnail-tag">UIST 2022</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="https://dl.acm.org/doi/pdf/10.1145/3526113.3545660" target="_blank">Threddy: An Interactive System for Personalized Thread-based Exploration and Organization of Scientific Literature</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang</span>, Joseph Chee Chang, Yongsung Kim, Aniket Kittur
</div>
<div class="venue">
<span class="uist-tag venue">UIST 2022</span>
[<a class="link" href="https://dl.acm.org/doi/pdf/10.1145/3526113.3545660" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/10.1145/3526113.3545660" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="uist2022-threddy-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="uist2022-threddy-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="uist2022-threddy-endnote" class="link">EndNote</span>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
Reviewing the literature to understand relevant threads of past work is a critical part of research and vehicle for learning. However, as the scientific literature grows the challenges for users to find and make sense of the many different threads of research grow as well. Previous work has helped scholars to find and group papers with citation information or textual similarity using standalone tools or overview visualizations. Instead, in this work we explore a tool integrated into users' reading process that helps them with leveraging authors' existing summarization of threads, typically in introduction or related work sections, in order to situate their own work's contributions. To explore this we developed a prototype that supports efficient extraction and organization of threads along with supporting evidence as scientists read research articles. The system then recommends further relevant articles based on user-created threads. We evaluate the system in a lab study and find that it helps scientists to follow and curate research threads without breaking out of their flow of reading, collect relevant papers and clips, and discover interesting new articles to further grow threads.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2022AUGMENTATION.png" alt="An example indirect author-based relevance message augmenting the incoming new paper recommendaiton."/>
<span class="thumbnail-tag">CHI 2022</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/KANG2022-from-who-you-know-to-what-you-read.pdf" target="_blank">From Who You Know to What You Read: Augmenting Scientific Recommendations with Implicit Social Networks</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang</span>, Rafal Kocielnik, Andrew Head, Jiangjiang Yang, Matt Latzke, Aniket Kittur, Daniel Weld, Doug Downey, and Jonathan Bragg
</div>
<div class="venue">
<span class="chi-tag venue">CHI 2022</span>
[<a class="link" href="files/KANG2022-from-who-you-know-to-what-you-read.pdf" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/10.1145/3491102.3517470" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="chi2022-from-who-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="chi2022-from-who-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="chi2022-from-who-endnote" class="link">EndNote</span>]
</div>
<div id="div-ref-block" class="border-dashed last med-line-height">
Finding and engaging with the relevant scientific knowledge is foundational for intellectual progress in a society. Yet, with an exponential growth in publication rates, this becomes a challenging task. While personalized recommendations can help, they still may lack explanations of how certain papers are relevant and thus should be prioritized or attended to. To combat this, we developed a citation-based and two kinds of social relation-based approaches to boost user engagement with scholarly paper recommendations. For users who opted in, these approaches augmented paper recommendations included in email alerts with textual relevance descriptions underneath the recommendations. We evaluated our approaches in a randomized field experiment that ran for over two months and with 7,000+ users, and also in a controlled lab study (N=14) for deeper qualitative insights. We report on our findings and implications for the design of future approaches that aim to augment scholarly recommendations.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2022Functional.png" alt="A functional graph representation using the extracted purposes of product ideas"/>
<span class="thumbnail-tag">CHI 2022</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/HOPE2022-Scaling.pdf" target="_blank">Scaling Creative Inspiration with Fine-Grained Functional Asepcts of Ideas</a>
</div>
<div class="first-few authors">
Tom Hope, Ronen Tamari, <span class="bold">Hyeonsu Kang</span>, Daniel Hershcovich, Joel Chan, Aniket Kittur, and Dafna Shahaf
</div>
<div class="venue">
<span class="chi-tag venue">CHI 2022</span>
[<a class="link" href="files/HOPE2022-Scaling.pdf" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/10.1145/3491102.3517434" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="chi2022-scaling-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="chi2022-scaling-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="chi2022-scaling-endnote" class="link">EndNote</span>]
</div>
<div class="border-dashed last">
We explore a novel representation for automatically breaking up product ideas described in natural language into fine-grained functional aspects. This representation can capture the core purposes and mechanisms in ideas, and support the backbone interactions (e.g., functional search of ideas, mapping and exploration of the design space around a focal problem) for augmenting human intelligence and accelerating the rate of innovation.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2018PARAGON.png" alt="A diagrammatic representation of the idea of Paragon"/>
<span class="thumbnail-tag">CHI 2018</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/KANG2018-Paragon.pdf" target="_blank">Paragon: An Online Gallery for Enhancing Design Feedback with Visual Examples</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang</span>, Gabriel Amoako, Neil Sengupta, Steven Dow
</div>
<div class="venue">
<span class="chi-tag venue">CHI 2018</span>
[<a class="link" href="files/KANG2018-Paragon.pdf" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/10.1145/3173574.3174180" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="chi2018-paragon-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="chi2018-paragon-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="chi2018-paragon-endnote" class="link">EndNote</span>]
</div>
<div class="border-dashed last">
<i>“A picture is worth a thousand words.”</i> We developed <i>Paragon</i>, a system that supports crowdworkers and peers during feedback exchange by enabling search of design examples that supplement the written feedback. In two lab studies, we found that i) feedback providers select poster examples that complement their feedback and align with a provided rubric and that ii) feedback providers give significantly more specific, actionable, and novel input when using an example-centric approach, as opposed to text alone.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2017OMNICODE.png" alt="An example of bidirectional code and visualization linking." />
<span class="thumbnail-tag">UIST 2017</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/KANG2017-Omnicode.pdf" target="_blank">Omnicode: A Novice-Oriented Live Programming Environment with Always-On Run-Time Value Visualizations</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu Kang</span>, Philip Guo
</div>
<div class="venue">
<span class="uist-tag venue">UIST 2017</span>
[<a class="link" href="files/KANG2017-Omnicode.pdf" target="_blank">PDF</a>
<span> · </span>
<a class="link" href="https://dl.acm.org/doi/10.1145/3126594.3126632" target="_blank">ACM DL</a>
<span> · </span>
<span class="ref link" id="uist2017-omnicode-bibtex" class="link">BibTeX</span>
<span> · </span>
<span class="ref link" id="uist2017-omnicode-acmref" class="link">ACM Ref</span>
<span> · </span>
<span class="ref link" id="uist2017-omnicode-endnote" class="link">EndNote</span>]
</div>
<div class="border-dashed last">
We developed <i>Omnicode</i>, a programming environment with an always-on run-time visualization that helps novice programmers directly see how the variables and their relations change in real-time, in response to the changes they make in the program code. In our lab study, we found <i>Omnicode</i> to be useful for debugging, forming proper mental models, explaining their code to others, and discovering moments of serendipity that would not have been likely within an ordinary IDE.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2023-BioSpark.png" alt="BioSpark main interface featuring a board of biological analogical mechanism images with four interaction features: Explain, Compare, Combine, and Critique."/>
<span class="thumbnail-tag">NeurIPS 2023</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="https://neurips.cc/virtual/2023/75052" target="_blank">BioSpark: An End-toEnd Generative System for Biological-Analogical Inspirations and Ideation</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang</span>, David Chuan-En Lin, Nikolas Martelaro, Aniket Kittur, Yan-Ying Chen, Matthew K. Hong
</div>
<div class="venue">
<span class="ci-tag venue">NeurIPS 2023 Creativity Workshop</span>
[<a class="link" href="https://neurips.cc/virtual/2023/75052" target="_blank">Poster</a>]
</div>
<div class="border-dashed last">
Nature is often used to inspire solutions for complex engineering problems, but achieving its full potential is challenging due to difficulties in discovering relevant analogies and synthesizing from them.
Here, we present an end-to-end system, BioSpark, that generates biological-analogical mechanisms and provides an interactive interface to comprehend and synthesize from them.
BioSpark pipeline starts with a small seed set of mechanisms and expands it using an iteratively constructed taxonomic hierarchies, overcoming data sparsity in manual expert curation and limited conceptual diversity in automated analogy generation via LLMs.
The interface helps designers with recognizing and understanding relevant analogs to design problems using four main interaction features.
We evaluate the biological-analogical mechanism generation pipeline and showcase the value of BioSpark through case studies.
We end with discussion and implications for future work in this area.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2022-naacl.png" alt="A diagrammatic representation of the system implementation consisting of three main components: Aspect-based querying; Global domain cluster generation; Local domain cluster generation"/>
<span class="thumbnail-tag">NAACL 2022</span>
</div>
<div class="flex-column">
<div class="first-few">
<a class="link" href="files/KANG2022-naacl-augmenting-with-retrieval-across-domains.pdf" target="_blank">Augmenting Scientific Creativity with Retrieval across Knowledge Domains</a>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu B. Kang*</span>, Sheshera Mysore*, Kevin Huang*, Haw-Shiuan Chang, Thorben Prein, Andrew McCallum, Aniket Kittur, Elsa Olivetti
</div>
<div class="venue">
<span class="ci-tag venue">NAACL 2022 Workshop</span>
[<a class="link" href="files/KANG2022-naacl-augmenting-with-retrieval-across-domains.pdf" target="_blank">PDF</a>
<span> · </span>
<span class="ref link" id="naacl2022-retrieval-across-bibtex" class="link">BibTeX</span>]
</div>
<div class="border-dashed last">
Exposure to ideas in domains outside a scientist's own may benefit her in reformulating existing research problems in novel ways and discovering new application domains for existing solution ideas. While improved performance in scholarly search engines can help scientists efficiently identify relevant advances in domains they may already be familiar with, it may fall short of helping them explore diverse ideas <i>outside</i> such domains. In this paper we explore the design of systems aimed at augmenting the end-user ability in cross-domain exploration with flexible query specification. To this end, we develop an exploratory search system in which end-users can select a portion of text core to their interest from a paper abstract and retrieve papers that have a high similarity to the user-selected core aspect but differ in terms of domains. Furthermore, end-users can 'zoom in' to specific domain clusters to retrieve more papers from them and understand nuanced differences within the clusters. Our case studies with scientists uncover opportunities and design implications for systems aimed at facilitating cross-domain exploration and inspiration.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2019-quadrants.png" alt="A 2-D distribution of project ideas based on their similarity to the source project's problem and solution ideas"/>
<span class="thumbnail-tag">CI 2019</span>
</div>
<div class="flex-column">
<div class="first-few">
<span>Matching Open Innovation Projects for Analogical Feedback Exchange</span>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu Kang</span>, Felicia Ng, Aniket Kittur
</div>
<div class="venue">
<span class="ci-tag venue">Collective Intelligence 2019</span>
</div>
<div class="border-dashed last">
We developed an algorithm for matching teams in open innovation contests that tackle related conservataion challenges using diverse approaches, thereby encouraging the transfer of analogical inspirations between teams. To this end, our algorithm used pre-trained language models to encode the natural language text descriptions of team challenges and their solution approaches into a vector similarity space, then computed semantic similarity between them to systematically find teams tackling similar problems using diverse approaches, shown as a conducive mechanism for the transfer.
</div>
</div>
</div>
<div class="divider"></div>
<div class="flex-row pad">
<div class="flex-left-row image-container">
<img class="thumbnail" src="images/KANG2018-BLOCKS.png" alt="a While block program block in Starlogo Nova"/>
<span class="thumbnail-tag">SIGPLAN 2018</span>
</div>
<div class="flex-column">
<div class="first-few">
<span>Custom Blocks in StarLogo Nova: A Template-Based Approach to Abstraction for Improved Ease of Use and Expressive Power</span>
</div>
<div class="first-few authors">
<span class="bold">Hyeonsu Kang</span>, David Wu, David Wendel
</div>
<div class="venue">
<span class="splash-tag venue">SIGPLAN 2018</span>
</div>
<div class="links">
</div>
<div class="border-dashed last">
We developed a general extension to the <a class="link" href="https://www.slnova.org/" target="_blank">StarLogo Nova</a> language to support end-user programming in various disciplines such as evolutionary biology, physics, and ecosystem sciences. This extension allowed end-users to select blocks that correspond to low-level programming constructs such as looping and variable assignment statements, and group them to create abstraction blocks that hide the low-level implementation details that oft-times distract learners from disciplinary learning objectives and system-level conceptual understanding. Using such abstraction blocks can also reduce the complexity of the programming language itself and lower the barrier to entry for novice learners.
</div>
</div>
</div>
</div>
</body>
</html>
Sitemap
Кол-во: 0
XML-карта сайта для поисковиков
?
Sitemap.xml помогает поисковику быстрее находить и индексировать страницы. Особенно важен для крупных сайтов и новых страниц, на которые ещё нет входящих ссылок.
Robots.txt не содержит ссылку на карту сайта. Рекомендуется добавить карту сайта и указать ссылку на нее в robots.txt.
Внутренние ссылки
Кол-во: 26
Ссылки на другие страницы своего сайта
?
Внутренние ссылки распределяют ссылочный вес между страницами и помогают поисковику обходить сайт. Пустые анкоры и ссылки на запрещённые robots.txt страницы — типичные ошибки.
Внутренних ссылок на странице 26 оптимально.
Внутренние ссылки не запрещены к индексации в robots.txt.
Показать внутренние ссылки
| Url | Анкор | Состояние | Анализировать |
|---|---|---|---|
| /files/cv-hyeonsu-kang.pdf |
CV
|
|
|
| /files/cv-hyeonsu-kang.pdf |
CV
|
|
|
| /files/KANG2025-BioSpark.pdf |
BioSpark
|
|
|
| /files/KANG2025-BioSpark.pdf |
BioSpark
|
|
|
| /files/users_mispredict_arxiv.pdf |
Users Mispredict Their Own Preferences for AI Writing Assistance
|
|
|
| /files/users_mispredict_arxiv.pdf |
PDF
|
|
|
| /files/KANG2025-VLM-SlideEval.pdf |
VLM-SlideEval: Evaluating VLMs on Structured Comprehension and Perturbation Sensitivity in PPT
|
|
|
| /files/KANG2025-VLM-SlideEval.pdf |
PDF
|
|
|
| /files/KANG2025-BioSpark.pdf |
BioSpark: Beyond Analogical Inspiration to LLM-augmented Transfer
|
|
|
| /files/KANG2025-BioSpark.pdf |
PDF
|
|
|
| /files/KANG2023-Synergi.pdf |
Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking
|
|
|
| /files/KANG2023-Synergi.pdf |
PDF
|
|
|
| /files/KANG2023-ComLittee.pdf |
ComLittee: Literature Discovery with Personal Elected Author Committees
|
|
|
| /files/KANG2023-ComLittee.pdf |
PDF
|
|
|
| /files/KANG2022-tochi-augmenting.pdf |
Augmenting Scientific Creativity with an Analogical Search Engine
|
|
|
| /files/KANG2022-tochi-augmenting.pdf |
PDF
|
|
|
| /files/KANG2022-from-who-you-know-to-what-you-read.pdf |
From Who You Know to What You Read: Augmenting Scientific Recommendations with Implicit Social Networks
|
|
|
| /files/KANG2022-from-who-you-know-to-what-you-read.pdf |
PDF
|
|
|
| /files/HOPE2022-Scaling.pdf |
Scaling Creative Inspiration with Fine-Grained Functional Asepcts of Ideas
|
|
|
| /files/HOPE2022-Scaling.pdf |
PDF
|
|
|
| /files/KANG2018-Paragon.pdf |
Paragon: An Online Gallery for Enhancing Design Feedback with Visual Examples
|
|
|
| /files/KANG2018-Paragon.pdf |
PDF
|
|
|
| /files/KANG2017-Omnicode.pdf |
Omnicode: A Novice-Oriented Live Programming Environment with Always-On Run-Time Value Visualizations
|
|
|
| /files/KANG2017-Omnicode.pdf |
PDF
|
|
|
| /files/KANG2022-naacl-augmenting-with-retrieval-across-domains.pdf |
Augmenting Scientific Creativity with Retrieval across Knowledge Domains
|
|
|
| /files/KANG2022-naacl-augmenting-with-retrieval-across-domains.pdf |
PDF
|
|
Внешние ссылки
Кол-во: 38
Ссылки на сторонние сайты
?
Исходящие внешние ссылки передают часть ссылочного веса на чужие сайты. Ссылки на авторитетные ресурсы безопасны; ссылки на мусорные сайты могут навредить репутации страницы.
Внешних ссылок на странице 38 слишком много. Спрячьте лишние ссылки в тег noindex или атрибут rel='nofollow'!
Показать внешние ссылки
| Url | Анкор | Анализировать |
|---|---|---|
| scholar.google.com |
Google Scholar
|
Анализировать url |
| semanticscholar.org |
Semantic Scholar
|
Анализировать url |
| scholar.google.com |
Google Scholar
|
Анализировать url |
| semanticscholar.org |
Semantic Scholar
|
Анализировать url |
| washingtonpost.com |
washingtonpost.com
|
Анализировать url |
| microsoft.com |
Link
|
Анализировать url |
| csail.mit.edu |
Nouran
|
Анализировать url |
| csail.mit.edu |
Nouran
|
Анализировать url |
| news.mit.edu |
MIT News
|
Анализировать url |
| microsoft.com |
Senior Applied Scientist at Microsoft
|
Анализировать url |
| allenai.org |
Allen Institute for AI (AI2)
|
Анализировать url |
| conservationx.com |
Conservation X Labs
|
Анализировать url |
| huggingface.co |
Zenodo
|
Анализировать url |
| dl.acm.org |
Mitigating Barriers to Public Social Interaction with Meronymous Communication
|
Анализировать url |
| dl.acm.org |
PDF
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| dl.acm.org |
PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers
|
Анализировать url |
| dl.acm.org |
PDF
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| dl.acm.org |
The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces
|
Анализировать url |
| dl.acm.org |
PDF
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| drive.google.com |
<span class="link">here</span>
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| drive.google.com |
<span class="link">here</span>
|
Анализировать url |
| github.com |
Dataset
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| dl.acm.org |
Threddy: An Interactive System for Personalized Thread-based Exploration and Organization of Scientific Literature
|
Анализировать url |
| dl.acm.org |
PDF
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| dl.acm.org |
ACM DL
|
Анализировать url |
| neurips.cc |
BioSpark: An End-toEnd Generative System for Biological-Analogical Inspirations and Ideation
|
Анализировать url |
| neurips.cc |
Poster
|
Анализировать url |
| slnova.org |
StarLogo Nova
|
Анализировать url |
Конкуренты Готовность: 0%
Конкуренты в Яндексе
Кол-во: 0
Топ сайтов-конкурентов в Яндексе
?
Сайты, чаще всего появляющиеся в ТОПе Яндекса по запросам из семантического ядра этой страницы.
Мы не нашли у вас конкурентов в Яндексе. Сайт или очень молодой или плохо продвигается.
Конкурентов в ТОП-10 Яндекса не нашлось.
Конкуренты в Google
Кол-во: 0
Топ сайтов-конкурентов в Google
?
Сайты, чаще всего появляющиеся в ТОПе Google по запросам из семантического ядра этой страницы.
Конкуренты в Google тоже не найдены. Займитесь продвижением сайта!
Конкурентов в ТОП-10 Google не нашлось.
ЗоЗПП: права потребителей Готовность: 100%
Нарушения
Не выявлены
Признаков дистанционной продажи товаров (интернет-магазина) не обнаружено — требования ЗоЗПП о раскрытии информации продавца к сайту не применяются. Нарушений нет.
ФЗ-149: рекомендательные технологии Готовность: 100%
Нарушения
Не выявлены
Рекомендательные блоки («с этим покупают», «похожие товары» и т.п.) на сайте не обнаружены — требования ст. 10.7 ФЗ-149 к сайту не применяются. Нарушений нет.
ФЗ-38: реклама Готовность: 100%
Нарушения
Не выявлены
Рекламных тематик с обязательными оговорками (медицина, БАД, кредиты и займы, новостройки) на сайте не обнаружено. Нарушений нет.
ФЗ-436: защита детей Готовность: 100%
Нарушения
Не выявлены
Признаков информационной продукции (новости, видео, книги, игры, курсы) не обнаружено — обязательная возрастная маркировка по ФЗ-436 сайту не требуется. Нарушений нет.
Вердикт
Таким сайт hyeonsukang.com видят поисковые системы. Процент оптимизации невысокий - 36%. Чтобы улучшить сайт и попасть в ТОП необходимо:
Постарайтесь исправить общие ошибки.
Исправьте ошибки в мета-тегах.
Исправьте ошибки оптимизации.
Исправьте ошибки индексации.
Поделитесь с друзьями: