Chatbots to Aid in Mental Health

We envision a world in which talk therapy can be given by a computer, exactly where and when it is needed. Recent advances in Natural Language Processing (NLP) and Deep Learning, have provided new ways to bring this vision to a reality.

The focus of the first project is to apply a known and structured therapeutic technique (Motivational Interviewing) to a specific problem in addiction (Smoking Cessation).  

It is a collaboration with the Nicotine Dependence Clinic at the Centre for Addiction and Mental Health and with the iSchool at the University of Toronto.

The first prototype chatbot was developed by Fahad Almusharraf in his M.A.Sc. thesis the first part of which (describing the design of the bot) was published in this paper.  This bot makes use of an NLP classifier to provide specific relevant reflections and responses to subjects who describe the reasons for and against smoking. The second paper (which describes the effect of the intervention) is described in detail in this paper

This work is a more  advanced bot, that we continue to work on, using zero shot, few shot generation, and fine-tuning techniques with transformer architectures. It it is related to the work on reflection generation from the University of Michigan.

Collaborators:  Dr. Peter Selby, Head of the Nicotine Dependence Clinic, CAMH

Graduate Students:  Fahad Almusharraf, Imtihan Ahmed, Ash Kumar, Mohamed Abdelwahab, Jiading Zhu

Undergraduate Students: Eric Keilty, Yanisa Khambanonda, Arnaud Deza, Marc Morcos, Avi Kraft, Vidya Sujaya, Leon Zhu, Angus Wang, Cindy Wang, Alec Dong

Press

“Could AI Help You Quit an Addiction?”

U of T researchers are developing a chatbot to help people stop smoking. One day, it might offer therapy, too.  University of Toronto Magazine, January 2024.

Publications 

Jonathan.Rose@utoronto.ca

The Edward S. Rogers Sr. Department of Electrical and Computer  Engineering,

Faculty of Applied Science and Engineering, University of Toronto