CommunityPulse

Increased access to online engagement platforms has created a shift in civic practice, enabling civic leaders to broaden their outreach to collect a larger number of community input, such as comments and ideas. However, sensemaking of such input remains a challenge due to the unstructured nature of text comments and ambiguity of human language. Hence, community input is often left unanalyzed and unutilized in policymaking. In this project, we explore how visual analytics can be used to surface critical insights from public input to enable civic leaders to make more informed decisions.

First, we interviewed 14 civic leaders to understand their practices and requirements. We identified challenges around organizing the unstructured community input and surfacing community's reflections beyond binary sentiments. Based on these insights, we built CommunityPulse, an interactive system that combines text analysis and visualization to scaffold different facets of community input. Our evaluation with another 15 experts suggests CommunityPulse's efficacy in surfacing multiple facets such as reflections, priorities, and hidden insights while reducing the required time, effort, and expertise for community input analysis.

We also explored the design of such visual analytics systems while considering their adherence towards analytical and political aspects of digital civics. To span this gap between political context and analytic framing, we proposed a series of two-pole conceptual dimensions, such as from singular user to multiple relationships, and from complexity to inclusivity of visualization design. For each dimension, we discuss how the tensions between these poles can help surface the political ramifications of design decisions in civic text visualization. These dimensions can thus help visualization researchers, designers, and practitioners attend more intentionally to these political aspects and inspire their design choices.


Team Members

Mahmood Jasim
Eric P.S. Baumer
Ali Sarvghad
Enamul Hoque
Narges Mahyar


Demo

https://communitypulse.cs.umass.edu/


Talk

CommunityPulse: Facilitating Community Input Analysis by Surfacing Hidden Insights, Reflections, and Priorities


Award

Honorable Mention Award, Designing Interactive Systems (DIS), 2021

Best Paper Award, Eurographics Working Group Conference on Data Visualization (EuroVis), 2022


Related Publications
[Best Paper Honorable Mention Award] CommunityPulse: Facilitating Community Input Analysis by Surfacing HiddenInsights, Reflections, and Priorities. Mahmood Jasim, Enamul Hoque, Ali Sarvghad, Narges Mahyar. 2021. Designing Interactive Systems (DIS).
[Best Paper Award] Of Course it's Political! A Critical Inquiry into Underemphasized Dimensions in Civic Text Visualization. Eric P. S. Baumer, Mahmood Jasim, Ali Sarvghad, and Narges Mahyar. 2022. Computer Graphics Forum 41, 3 (EuroVis).
Designing Technology for Sociotechnical Problems: Challenges and Considerations. Narges Mahyar, Mahmood Jasim, Ali Sarvghad. 2020. IEEE computer graphics and applications.
Towards Understanding Desiderata for Large-Scale Civic Input Analysis. Mahmood Jasim, Ali Sarvghad, Enamul Hoque, Narges Mahyar. 2020. Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems.