Projects

Contextual Bandits

Contextual bandit algorithms  are a powerful reinforcement learning techniques that enable personalization and user-focused design. They balance exploration of new possibilities with exploitation of the best existing options to learn and act optimally. Our lab conducts research on contextual bandits and their applications to various areas of human-computer interaction, such as encouraging people to exercise, where we use them to balance showing people new motivational messages with showing them those that have been proven to be effective in the past.


Mental Health

Mental health is an area where people can benefit especially from personalization and user-focused design. We have two main focuses in our mental health projects. First, we are working on using machine learning to deploy personalized stress management interventions for students to help them handle stress. Secondly, we are working on deploying and measuring the effect of TenQ, a condensed ten-question survey informed by cognitive behavioural therapy that helps people reflect on their mental health. Our goal with this is to lower the barrier to accessing mental health resources.


DIAMANTE

The DIAMANTE focuses on the intersection of physical and mental health in patients with both diabetes and depression. The project takes the form of an app where participants articulate a target number of steps walked daily and fill out a survey. We then apply contextual bandits to determine which factors are effective to help users reach their step goals and improve their mental health. The app sends both motivational messages and requests for feedback to the users. For the first six days, it also sends one message per day with advice on managing diabetes and depression and asks the participant to rate their mood


Exercise

We see great potential in the application of intelligent adaptive interventions to helping people stick to their exercise schedules. We are working with Goodlife Fitness to apply findings from the psychology of motivation and self-control in an automated text messaging system. We use reinforcement learning to send participants automated motivational text messages to encourage them to go to the gym and help them meet their exercise goals.


Personalized Explanations

There is a large body of academic literature showing that students learn better when they write explanations of the concepts they are learning. This is great in a lab setting when we can ensure that students who participate in a study take the time to write out an explanation, but how can we embed self-explanation into courses? In the personalized explanations project, we design randomized experiments to determine how to get students to write self-explanations in online learning systems.