Using Adaptive Bandit Experiments to Increase and Investigate Engagement in Mental Health


  • Harsh Kumar University of Toronto
  • Tong Li University of Toronto
  • Jiakai Shi University of Toronto
  • Ilya Musabirov University of Toronto
  • Rachel Kornfield Northwestern University
  • Jonah Meyerhoff Northwestern University
  • Ananya Bhattacharjee University of Toronto
  • Chris Karr Audacious Software
  • Theresa Nguyen Mental Health America
  • David Mohr Northwestern University
  • Anna Rafferty Carleton College
  • Sofia Villar University of Cambridge
  • Nina Deliu University of Cambridge Sapienza University of Rome
  • Joseph Jay Williams University of Toronto



Human-Computer Interaction , Health, Medical & Medicine , Multidisciplinary Topics and Applications , Recommendation Systems , Track: Emerging Applications


Digital mental health (DMH) interventions, such as text-message-based lessons and activities, offer immense potential for accessible mental health support. While these interventions can be effective, real-world experimental testing can further enhance their design and impact. Adaptive experimentation, utilizing algorithms like Thompson Sampling for (contextual) multi-armed bandit (MAB) problems, can lead to continuous improvement and personalization. However, it remains unclear when these algorithms can simultaneously increase user experience rewards and facilitate appropriate data collection for social-behavioral scientists to analyze with sufficient statistical confidence. Although a growing body of research addresses the practical and statistical aspects of MAB and other adaptive algorithms, further exploration is needed to assess their impact across diverse real-world contexts. This paper presents a software system developed over two years that allows text-messaging intervention components to be adapted using bandit and other algorithms while collecting data for side-by-side comparison with traditional uniform random non-adaptive experiments. We evaluate the system by deploying a text-message-based DMH intervention to 1100 users, recruited through a large mental health non-profit organization, and share the path forward for deploying this system at scale. This system not only enables applications in mental health but could also serve as a model testbed for adaptive experimentation algorithms in other domains.



How to Cite

Kumar, H., Li, T., Shi, J., Musabirov, I., Kornfield, R., Meyerhoff, J., Bhattacharjee, A., Karr, C., Nguyen, T., Mohr, D., Rafferty, A., Villar, S., Deliu, N., & Williams, J. J. (2024). Using Adaptive Bandit Experiments to Increase and Investigate Engagement in Mental Health. Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 22906-22912.