What does the public want their local government to hear?

​​Public comments at city council meetings are often seen as a way for residents to raise local issues like housing, infrastructure or public services. But new research from the University of Michigan School of Information shows that these meetings are also a major venue for expressing broader societal concerns, including democracy, equity and social justice.

UMSI PhD student Chang Ge’s paper, “What does the public want their local government to hear? A data-driven case study of public comments across the state of Michigan,” analyzes public comments from city council meetings in 15 cities across Michigan. Drawing on recordings archived on platforms such as YouTube, the study introduces a framework for categorizing comments along two dimensions: local concerns, such as housing or election administration, and societal concerns, such as functional democracy or anti-racism.

“This project began in 2023, when I became fascinated by city council meetings,” Ge says. “I was curious about what people actually discuss in these settings, yet I found very little systematic research on the content of public comments.” 

The paper was published in the January issue of the Journal of Quantitative Description: Digital Media and is co-written by Justine Zhang, Haofei Xu, Yanna Krupnikov, Jenna Bednar and Sabina Tomkins. 

Using machine learning methods, Ge and her co-authors developed data-driven taxonomies of local and societal concerns and applied them to the meetings. One of the study’s most surprising findings, Ge says, is how frequently members of the public raise national and societal issues in meetings that are typically considered hyperlocal forums. 

“Moving forward, we plan to expand this work nationwide to understand how often societal issues appear in city council meetings across the U.S., and which kinds of societal concerns are emphasized in different states,” she says. 

Ge is a fifth-year student advised by UMSI assistant professor Sabina Tomkins. She expects to graduate in May 2027. Her research focuses on political science and data science, using tools such as machine learning and natural language processing to study democratic processes in the U.S. Before joining UMSI, Ge earned a Bachelor of Business Administration at Shanghai University and a Master of Arts in Applied Economics at U-M. 

This is her first published paper, a milestone in a PhD student’s career, initiating them into the scholarly community as producers of knowledge. UMSI supports their work as part of our mission to share knowledge.

During her master’s program, she worked as a research assistant for UMSI assistant professor Yan Chen while taking MSI programming courses, which led her to pursue doctoral research at UMSI. 

“What I love most about being at UMSI is the freedom to do genuinely interdisciplinary work,” Ge says. “It’s the rare place where I’ve been able to blend behavioral economics with machine learning and natural language processing in ways that resonate with both economics journals and computational social science audiences.” 

Read “What does the public want their local government to hear? A data-driven case study of public comments across the state of Michigan” in the January issue of the Journal of Quantitative Description: Digital Media. The paper was co-written by Justine Zhang, Haofei Xu, Yanna Krupnikov, Jenna Bednar and Sabina Tomkins. See the abstract below: 

City council meetings are vital sites for civic participation where the public can speak directly to their local government. By addressing city officials and calling on them to take action, public commenters can potentially influence policy decisions spanning a broad range of concerns, from housing, to sustainability, to social justice. Yet studies of these meetings have often been limited by the availability of large-scale, geographically-diverse data. Relying on local governments' increasing use of YouTube and other technologies to archive their public meetings, we propose a framework that characterizes comments along two dimensions: the local concerns where concerns are situated (e.g., housing, election administration), and the societal concerns raised (e.g., functional democracy, anti-racism). Based on a large record of public comments we collect from 15 cities in Michigan, we produce data-driven taxonomies of the local concerns and societal concerns that these comments cover, and employ machine learning methods to scalably apply our taxonomies across the entire dataset. We then demonstrate how our framework allows us to examine the salient local concerns and societal concerns that arise in our data, as well as how these aspects interact.

RELATED

Learn more about UMSI PhD student Chang Ge by visiting her UMSI profile. 

Read about UMSI’s PhD in Information program today!