Joseph Jay Williams & Intelligent Adaptive Interventions Lab

Welcome to this unique, in-progress hybrid transformation of Joseph Jay Williams' homepage into the Intelligent Adaptive Interventions lab's homepage!

The research agenda of my Intelligent Adaptive Interventions group is guided by redesigning technology for people, with applications like education and health behavior change. We combine human-computer interaction and psychology by conducting randomized A/B comparisons in real-world settings (e.g. online homework, text messaging interventions, apps). We apply statistics and machine learning methods like multi-armed bandit algorithms to dynamically adapt randomized A/B comparisons to enhance and personalize the experience for future people, balancing practical impact with conducting scientific research.

We are accepting applications for PhD programs for Fall 2022 entry from both Domestic and International students! Apply before Dec, 1st 2021 to UofT programs in Computer Science, Psychology or before Nov, 15th 2021 to Statistics. If you are interested in one of our research directions start preparing your application today!
We are looking for students with a variety of academic backgrounds, some examples are: HCI, Psychology, Mental Health, Machine Learning + Statistics.
We welcome applications from groups, underrepresented in CS and Stats. Our current students will try to provide short feedback on the expressions of interest of students from such groups, if sent before the deadline to

Slides and recordings of overview talks are: Slides for broad HCI audience, Recording for broad HCI audience (45 min), Slides for education audience, Recording of TEDxPortofSpain talk.
I am an Assistant Professor in the Department of Computer Science at the University of Toronto, with courtesy cross-appointments in the Department of Psychology and Statistics, and I'm a faculty affiliate at the Vector Institute for Artificial Intelligence. I was previously an Assistant Professor at the School of Computing (Information Systems & Analytics, and NUS HCI Lab) at National University of Singapore (NUS), and did Research Fellow positions at Harvard and Stanford, after receiving my PhD in Computational Cognitive Science from UC Berkeley.

Dynamic Experimentation       

One example of my research is a system I created for automatically experimenting with explanations, which enhanced learning from math problems as much as an expert instructor [LAS 2016]. Another system boosted people's responses to an email campaign, by dynamically discovering how to personalize motivational messages to a user's activity level [EDM 2015].

These successful applications are enabled by my integrative approach: I use my cognitive science theories in deciding the target actions for experimentation (e.g. explanations, motivational messages) and the metrics to optimize (e.g. student ratings, response rates). To generate new actions I design crowdsourcing workflows, leveraging my human-computer interaction research. Data from experiments is analyzed using methods from Bayesian statistics, and algorithms from machine learning are used to turn data into dynamic enhancement and personalization of users' experiences. My self-improving systems are powered by combining human intelligence – in generating hypotheses that can be tested with data – with statistical machine learning – to automate rapid iteration and improvement.
My TEDxPortofSpain talk explains how I use this approach in education, using MOOClets to intelligently adapt explanations for how to solve math problems. 

You can contact me at: If you are interested in joining my group, you can email

Office: Directions at

TEDxPortofSpain: Is the internet replacing teachers?

News & Updates

More about my research

In blending scientific research and applications I collaborate and consult with domain/topic experts, instructors, designers, and researchers from diverse disciplines like education, psychology, and computer science. I draw on theories and methodology from research I have done, as well as synthesizing findings from other scientists, work on behavior change, reviews of evidence-based best practices for teaching and learning, practical experience as a statistics tutor, evaluations of educational technology products & authoring tools for e-learning, experience as an ed-tech consultant and science & technology advisor, and my own active development of interactive learning and behavior change resources

I am currently an Assistant Professor in Computer Science at the University of Toronto (with a Graduate appointment in Psychology and Statistics). Previously I was an Assistant Professor in the School of Computing (Information Systems & Analytics, and NUS HCI Lab) at National University of Singapore (NUS). Prior to that I was a Research Fellow at Harvard's VPAL (Vice Provost for Advances in Learning) Research Group, and a member of the Intelligent Interactive Systems group led by Krzysztof Gajos in Computer Science. I have a courtesy appointment as a Research Scientist in Computer Science at Worcester Polytechnic Institute, where I am a co-PI with Neil Heffernan on an NSF Cyberinfrastructure grant. We use the ASSISTments K12 online math platform to crowdsource randomized controlled trials from the broader scientific community. 

I was previously a postdoc at Stanford University in the Graduate School of Education and Lytics Lab, working with the Office of the Vice Provost for Online Learning and Candace Thille's Open Learning Initiative. I received my PhD in Computational Cognitive Science from UC Berkeley's Psychology Department. I worked with Tania Lombrozo to investigate why prompting people to explain "why?" helps learning, and with Tom Griffiths on using Bayesian statistics and methods from machine learning to characterize learning, reasoning, and judgment.