Participation and Representation in Local Government Speech

2026-04-22

AI Summary

This study addresses the lack of systematic empirical analysis of public participation in local legislative bodies, a gap constrained by limited data scale and spatiotemporal coverage. The authors construct the largest dataset to date of municipal government meeting audio recordings, encompassing over a decade of city council proceedings from 115 California municipalities. Leveraging advanced speech transcription and speaker diarization techniques, the research provides the first systematic evidence of demographic biases among participants and their relationship to institutional design. Findings reveal that participants are disproportionately older, White, male, politically liberal, and homeowners; land-use topics significantly increase participation rates; and while eliminating remote access reduces the number of speakers, it does not substantially alter participant composition. These results advance understanding of representativeness in local democracy and the mechanisms through which institutional arrangements shape civic engagement.

Technology Category

• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Knowledge Representation and Reasoning: Preferences
• Machine Learning: Ethics, Bias, and Fairness

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Local government meetings are the most common formal channel through which residents speak directly with elected officials, contest policies, and shape local agendas. However, data constraints typically limit the empirical study of these meetings to agendas, single cities, or short time horizons. We collect and transcribe a massive new dataset of city council meetings from 115 California cities over the last decade, using advanced transcription and diarization techniques to analyze the speech content of the meetings themselves. We document two sets of descriptive findings: First, city council meetings are frequent, long, and vary modestly across towns and time in topical content. Second, public participants are substantially older, whiter, more male, more liberal, and more likely to own homes than the registered voter population, and public participation surges when topics related to land use and zoning are included in meeting agendas. Given this skew, we examine the main policy lever municipalities have to shift participation patterns: meeting access costs. Exploiting pandemic-era variation in remote access, we show that eliminating remote options reduces the number of speakers, but does not clearly change the composition of speakers. Collectively, these results provide the most comprehensive empirical portrait to date of who participates in local democracy, what draws them in, and how institutional design choices shape both the volume and composition of public input.

Problem

• local government
• public participation
• representation
• city council meetings
• institutional design

Innovation

• speech transcription
• speaker diarization
• local government meetings
• public participation
• computational social science