When a natural disaster, terrorist attack, or any other crisis strikes, the best time to act isn’t just as it occurs, but rather in the months, even years, before it happens.

Modern-day learners have a wealth of “teachers” to turn to: online books, e-learning courses, YouTube tutorials, and even smartphone apps. If, for instance, you are yearning to lead a more mindful existence and seek everyday calm through the practice of meditation, you might download an app to guide you along.

Imagine if Amazon Alexa could recommend a tub of ice cream or Siri could play a cheerful song if they hear sadness in your voice. AI voice recognition can now recognise emotions with very high accuracy. Yet it is not correct all the time, and this begs the question of how it make its decisions.

As COVID crept across the world, confining people to their homes and chaining them to their desks — for work, school, and play — Zhao Shengdong was no exception. Involved in class after online class, the associate professor at NUS Computing and his PhD student Ashwin Ram soon began to wonder: What can we do to enhance the online learning experience? Instead of a static setting, could people learn dynamically on-the-go instead?