AI & Fundamentals

Changing Behaviour using AI and Experimentation: Applications in Education, Health Behaviour, Marketing, Website Design - Joseph Jay Williams, Assistant Professor, Computer Science, University of Toronto

Zoom Link
 

Abstract:

How can we change people's behaviour to help them achieve their goals? This lecture presents tools and methods for optimizing a product or intervention by making it Intelligent and Adaptive, including: (1) Messages/Prompts in Mobile Apps; (2) Explanations of concepts in websites; (3) Texts & Emails for Marketing & Health. This work is based on the AdapEx framework,which recently received 1st prize in the $1M Xprize competition for future of experimentation, to transform components of an interface into Intelligent agents, that integrate human intelligence (crowdsourcing) and artificial intelligence (LLMs). These components become Adaptive by using perpetually MicroExperiments to test out these different actions, and using qualitative and quantitative data to optimize what to show to a user/customer, in different contexts. We show how to use AdapComps to integrate AI/LLMs, Machine Learning for adaptive experiments, theories of psychology, and human-computer interaction/user experience design.

Bio:

Joseph Jay Williams is an Assistant Professor at the University of Toronto in Computer Science, with courtesy appointments supervising PhD students in Statistical Science, Psychology, and the Vector Institute for Artificial Intelligence, and courtesy appointments in Economics & Industrial Engineering. He directs the Intelligent Adaptive Interventions lab, which aims to transform any user interface into an Intervention to help people change their behaviour and learn, by reimagining randomized "A/B" experiments as a tool for Intelligent Adaptation. Our lab's work is represented in over 80 papers (www.intadaptint.org/papers), 2 Best Paper Awards (1 at CHI), 4 Runner Up/Honorable Mention for Best Paper (CHI, EDM, LAS), and 1st place in a $1M Xprize competition for the future of experimentation technology in education. We've received over $2M in grant funding, enabling interventions impacting over 500 000 people. Our 10 PhD Students span HCI (Human Computer Interaction), Cognitive/Social/Clinical/Health Psychology, applied ML (reinforcement learning), applied AI (LLMs), & Statistics. Joseph was previously an Assistant Professor in Information Systems & Analytics at National University of Singapore, Research Scientist at Harvard, postdoc at Stanford, and did his PhD at UC Berkeley. He is originally from Trinidad and Tobago. Talks for different audiences are at www.intadaptint.org/representative-talks, and our research agenda on Intelligent Adaptive Experimentation is summarized at the URL tiny.cc/williamsresearch.

Zoom Link