SUDS project

Oct 05 2026

Automated text analysis of liberal and conservative news

Research description:

Using Big Data, text analysis, and machine learning techniques, we will examine how liberals and conservatives differ in their moral values, cognitive styles, antiscience attitudes, and other psychological characteristics. Specifically, we have access to more than 5 million news articles from about 500 media outlets. The outlets vary widely in ideological leaning, from far left to far right. They also vary in veracity, from mostly fact-checked to mostly fake, conspiracy, and pseudoscience news. Our team has already completed preprocessing of all the news articles. The SUDS Scholar will apply automated text analysis and machine learning techniques to these articles in order to identify linguistic patterns and biases depending on how liberal or conservative the media outlet is.

Year: 2023

Researcher:
Spike W.S. Lee, Joseph L. Rotman School of Management, University of Toronto

Student:
Akil Huang, University of Toronto

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more

Oct 05 2026

Applying Data Science Tools to Examine the Computational and Operational Principles of an Intact Neural System

Research description:

We combine cutting-edge imaging and computational biology tools to address how a nervous system develops and operates. In collaboration with the Center for Brian Science, Harvard University and a state-of-art imaging facility, we are pioneering the field of connectomics, where serial ultrathin electron microscopy (EM) images are used to map the wiring of whole nervous systems. Using datasets from animals at different developmental ages, and exposed to different environments, we can glean insights into the general principles of network assembly and plasticity (Witvliet Nature 2021; Mulcahy Current Biology 2022). In this project, research students will work on the development of automated image processing, segmentation, and volumetric reconstructing of circuits from EM image stacks, working with our team and collaborators currently building machine learning algorithms to address these challenges.

Year: 2023

Researcher:
Mei Zhen, Lunenfeld-Tanenbaum Research Institute

Student:
Congrong He, University of Toronto

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more

Oct 05 2026

Algorithms and Statistical Tests for Real-World Adaptive Experiments to Enhance and Personalize Technology Interventions for Education, Mental/Physical Health, & Behaviour Change

Research description:

These papers give a good sense. The SUDS Scholar will start by replicating this work, and then be involved in modifying/developing such algorithms for adaptive experimentation, and/or generalizing statistical hypothesis tests (or Bayesian analyses) for analyzing such data.

“Multi-armed bandit algorithms like Thompson Sampling can be used to conduct adaptive experiments, using data to progressively assign more participants to more effective arms. Such assignment strategies increase the risk of statistical hypothesis tests identifying a difference between arms when there is not one. We explore algorithms that combine the benefits of uniform randomization for statistical analysis, with the benefits of reward maximization achieved by Thompson Sampling (TS). TS PostDiff (Posterior Probability of Difference) takes a Bayesian approach to mixing TS and UR: the probability a participant is assigned using UR allocation is the posterior probability that the difference between two arms is `small’ (below a certain threshold), allowing for more UR exploration when there is little or no reward to be gained. We find that TS PostDiff method performs well across multiple effect sizes, and thus does not require tuning based on a guess for the true effect size.”

Year: 2023

Researcher:
Joseph Jay Williams, Department of Computer Science, Faculty of Arts & Science, University of Toronto

Student:
Andrew Chung, University of Toronto

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more

Oct 05 2026

Algorithmic (Un)Fairness in Biomedical Informatics: Where are we at?

Research description:

Machine learning (ML) has profound potential to make healthcare more accurate, accessible, and personalized. Today, ML models developed with medical images are being validated in clinical settings to expedite diagnosis in ophthalmology and radiology. Electronic health records (EHRs) are also being utilized to build ML systems for more inclusive clinical trials design so that study findings translate to clinical practice.
Progress withstanding, ML in healthcare faces significant ethical and methodological barriers. Ethically, it is evident that ML systems can reinforce inequity by perpetuating biases intrinsic to clinical data or poor design choices. Substantial differences in the accuracy of ML models across protected attributes such as race have been observed in numerous applications, recently in a state-of-the-art radiograph diagnostic model. To prevent ML from exacerbating inequity in healthcare, there is an urgent need to precisely measure and subsequently mitigate such algorithmic bias.

This project will examine the state of algorithmic (un)fairness within biomedical informatics. The SUDS Scholar will participate in a thorough literature review as well as several real data analyses (eg. EHRs, medical images) that illustrate the nuances of both identifying and measuring algorithmic bias in healthcare applications. The student will contribute to a manuscript for publication as well as open source software development.

Year: 2023

Researcher:
Jesse Gronsbell, Department of Statistical Sciences, Faculty of Arts & Science, University of Toronto

Student:
Yiwen Li, University of Toronto

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more

Oct 05 2026

Abnormal brain cell activity in a mouse model of Alzheimer’s disease

Research description:

Alzheimer’s disease (AD) slowly destroys memory and places tremendous emotional and financial burdens on family and caregivers. Thanks to past research, we now have a good understanding of how harmful proteins build up in brains with AD. But, we still do not know much about why protein buildup causes memory problems. To address this question, we investigate how these proteins disrupt brain activity patterns in a mouse AD model. Data collected from our experiments consists of vast quantities of time series data recorded in freely behaving mice.

The SUDS Scholar will work with two types of data, local field potentials (LFPs) and neuronal spiking activity. LFPs are rhythmic oscillatory activity patterns that reflect the summed activity of many neurons while spiking activity represents the action potentials of individual neurons. We will use several dimension reduction and machine learning approaches to isolate specific abnormalities in the oscillatory and spiking activity in the mouse AD model. We will also build a statistical model to infer cause-effect relationships between memory impairments and the detected abnormal patterns. The detected patterns could develop into a novel biomarker for AD that is indispensable for early and accurate diagnosis.

Year: 2023

Researcher:
Kaori Takehara, Department of Psychology, Faculty of Arts & Science, University of Toronto

Student:
Emily Zhang, McGill University

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.

Learn more