TY - GEN
T1 - PolicyPulse
T2 - 2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025
AU - Wang, Maggie
AU - Colby, Ella
AU - Okwara, Jennifer
AU - Rao, Varun Nagaraj
AU - Liu, Yuhan
AU - Monroy-Hernández, Andrés
N1 - Publisher Copyright:
© 2025 Copyright held by the owner/author(s).
PY - 2025/4/26
Y1 - 2025/4/26
N2 - Public opinion shapes policy, yet capturing it effectively to surface diverse perspectives remains challenging. This paper introduces PolicyPulse, an LLM-powered interactive system that synthesizes public experiences from online community discussions to help policy researchers author memos and briefs, leveraging curated real-world anecdotes. Given a specific topic (e.g., “Climate Change”), PolicyPulse returns an organized list of themes (e.g., “Biodiversity Loss” or “Carbon Pricing”), supporting each theme with relevant quotes from real-life anecdotes. We compared PolicyPulse outputs to authoritative policy reports. Additionally, we asked 11 policy researchers across multiple institutions in the Northeastern U.S to compare using PolicyPulse with their expert approach. We found that PolicyPulse’s themes aligned with authoritative reports and helped spark research by analyzing existing data, gathering diverse experiences, revealing unexpected themes, and informing survey or interview design. Participants also highlighted limitations including insufficient demographic context and data verification challenges. Our work demonstrates how AI-powered tools can help influence policy-relevant research and shape policy outcomes.
AB - Public opinion shapes policy, yet capturing it effectively to surface diverse perspectives remains challenging. This paper introduces PolicyPulse, an LLM-powered interactive system that synthesizes public experiences from online community discussions to help policy researchers author memos and briefs, leveraging curated real-world anecdotes. Given a specific topic (e.g., “Climate Change”), PolicyPulse returns an organized list of themes (e.g., “Biodiversity Loss” or “Carbon Pricing”), supporting each theme with relevant quotes from real-life anecdotes. We compared PolicyPulse outputs to authoritative policy reports. Additionally, we asked 11 policy researchers across multiple institutions in the Northeastern U.S to compare using PolicyPulse with their expert approach. We found that PolicyPulse’s themes aligned with authoritative reports and helped spark research by analyzing existing data, gathering diverse experiences, revealing unexpected themes, and informing survey or interview design. Participants also highlighted limitations including insufficient demographic context and data verification challenges. Our work demonstrates how AI-powered tools can help influence policy-relevant research and shape policy outcomes.
KW - automated synthesis
KW - human-AI interaction
KW - large language models
KW - online discourse analysis
KW - policy research
KW - prompt engineering
KW - qualitative analysis
KW - text analysis
UR - http://www.scopus.com/inward/record.url?scp=105005769847&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=105005769847&partnerID=8YFLogxK
U2 - 10.1145/3706599.3720266
DO - 10.1145/3706599.3720266
M3 - Conference contribution
AN - SCOPUS:105005769847
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI EA 2025 - Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
Y2 - 26 April 2025 through 1 May 2025
ER -