CHS: Small: Collaborative Research: Making Information Deserts Visible: Computational Models, Disparities in Civic Technology Use, and Urban Decision Making - Sub from University of Maryland

Project: Research project

Project Details

Description

CHS: Small: Collaborative Research: Making Information Deserts Visible: Computational Models, Disparities in Civic Technology Use, and Urban Decision Making - Sub from University of Maryland CHS: Small: Collaborative Research: Making Information Deserts Visible: Computational Models, Disparities in Civic Technology Use, and Urban Decision Making - Sub from University of Maryland CHS: Small: Collaborative Research: Making Information Deserts Visible: Computational Models, Disparities in Civic Technology Use, and Urban Decision Making - Sub from University of Maryland - Supplement This modification to the existing subaward will allow the University of Maryland to expand its subcontract to ASU for continued and expanded graduate student support on the CHS: Collaborative Research project, Making Information Deserts Visible: computational models, disparities in civic technology use, and urban decision making, that UMD and ASU have from NSF. The students will: 1. Conduct a literature review in related fields and topics that could be useful to analyze 311 data, including but not limited to information science, civic technology, public administration, digital divide, technology adoption, and civic engagement. Weve already reviewed much literature but still need more especially in information provision and information behavior. 2. Help develop theoretical frameworks to explore, interpret, understand, and explain the data analysis result. 3. Conduct a qualitative analysis, including interviewing city officials, government employees, contractors, and others to investigate how Boston and other cities launch, utilize, and improve 311 services, how the data is input, stored, and processed. It may also include interviewing citizens to gain an insight into whether and how they use 311 service, what reporting channels they prefer, what motivates them to use or not to use 311, etc.. 4. Conduct a quantitative analysis, including data cleaning, data wrangling, feature generation, statistical analysis, and machine learning. The data is mostly tabular data and geo data. One example of the currently on-going tasks is to develop a machine learning model to distinguish whether a user is a citizen or a government agency/employee based on certain generated features so that their behaviors can be studied separately. 5. Develop papers for journals, conferences, and workshops. 6. Create data visualization to present the data and results. This may involve website design and web app development.
StatusFinished
Effective start/end date1/1/218/31/22

Funding

  • National Science Foundation (NSF): $89,224.00

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.