Open-Source Data and AI Tools for Community Organizations

The Center for Social Science Scholarship (CS3) is pleased to host a workshop series focused on helping local community organizations with using open-source tools (R programming) and generative AI/LLMs for improving organizational effectiveness.  This series will begin with the basics of open-source tools like R and on developing an understanding of how best to use generative AI/LLMs within your organizations. Each session will include hands-on applications, and session topics may be adjusted based on the needs of participants.  This series is supported through the Open Research Community Accelerator and the University System of Maryland Wilson H. Elkins Professorship of Academic Transformation.

In-person sessions will be held at the University of Maryland, Baltimore County (1000 Hilltop Circle, Baltimore, MD 21250) and one session will be held at the Urban Institute (500 L’Enfant Plaza SW, Washington, DC 20024). Parking and lunch will be provided.

Session 1: Open-Source Computing Tools and AI Basics
Format:  Webex Webinar
Type: Introduction and Foundational
Date: August 4, 2026
Time: 10am – 12pm EST
Speaker: Dr. Eric Stokan
Community Workshop Flyer 8.4.26

Description:

This introductory session will provide an overview of the training series, including the topics, tools, and learning opportunities that will be offered. Participants will learn what is meant by open-source software, how open-source tools differ from commercial platforms, and which tools can support data management, analysis, visualization, and organizational decision-making.

The session will also introduce the fundamentals of artificial intelligence and generative AI. Topics will include:

  • What do we mean by artificial intelligence and generative AI?
  • What can—and cannot—current AI tools do?
  • What are appropriate use cases for nonprofit and community organizations?
  • What are the limitations and risks of using AI?
  • How can organizations use tools like R to automate processes, increase transparency, analyze, and visualize data?

A brief baseline survey will be administered before the session.  Participants may be eligible to earn UMBC microcrodential badges.

Session 2: Data Wrangling and Management with Open-Source Tools (R Programming)
Format: UMBC – Public Policy Building, Room 451
Type: Data Acquisition and Cleaning Lab
Date: Tuesday, August 11, 2026
Day/Time: 10am-2pm (Lunch provided)
Speaker: Eric Stokan

Description:

Many nonprofit and community organizations maintain information in Excel spreadsheets, CSV files, websites, PDFs, and other disconnected sources. This hands-on session will introduce participants to R, an open-source programming language, and demonstrate how it can be used to import, organize, combine, and clean organizational data.

Participants will practice addressing common data-management challenges, including:

  • Inconsistent names and formatting
  • Duplicate client or participant records
  • Blank or missing fields
  • Changes in program names or codes
  • Data stored across multiple spreadsheets
  • Merging datasets from different programs or reporting periods
  • Retrieving information from websites and other external sources

Participants will work in a cloud-based programming environment (Google Colab), and will learn how AI assistants such as Gemini can help explain, generate, and troubleshoot code when appropriate.

By creating transparent and reproducible workflows, organizations can reduce repetitive work, improve data quality, and move more efficiently from data collection to program evaluation and reporting.

A brief baseline survey will be administered before the session.  Participants may be eligible to earn UMBC microcrodential badges.

Session 3: Data Visualization and Dashboards

Primary tools: R, ggplot2, and Shiny
Format: UMBC – Public Policy Building, Room 451
Type: Hands-on visualization and dashboard lab
Date: Tuesday, August 18
Time: 10am-2pm (Lunch provided)
Speakers: Dr. Rebecca Williams and Krishna Chaitanya Mummadi

Description:

This session will help participants transform organizational data into clear, accurate, and compelling visualizations that can support grant applications, board presentations, program evaluation, community engagement, and communication with funders.

Participants will begin with the fundamentals of data visualization using the ggplot2 package in R. They will then explore how visualizations can be organized into interactive dashboards and shared with internal and external audiences.

The session will include opportunities to:

  • Use AI assistants to draft and troubleshoot ggplot2 code
  • Prepare data for visualization
  • Create charts, tables, figures, and summary statistics
  • Select appropriate visualizations for different questions and audiences
  • Improve colors, themes, titles, labels, and annotations
  • Review options for publishing dashboards and project websites

The session will emphasize thoughtful visualization choices so that participants can communicate findings accurately without obscuring uncertainty or oversimplifying results.

A brief baseline survey will be administered before the session.  Participants may be eligible to earn UMBC microcrodential badges.

Session 4: From Text to Insights: Using R, APIs, and AI for Community Data
Tools: R programming, Qualtrics, QualtricsR, and Google Form APIFormat:
In Person:  Urban Institute:  500 L’Enfant Plaza SW, Washington, DC 20024
Type: Hands-on text analysis and API lab
Date: Wednesday, August 26, 2026
Time: 10am-2pm (lunch provided)
Speaker: Dr. Eric Stokan

Description:

This hands-on session introduces community organizations to practical ways of using R, APIs, and artificial intelligence to work with textual data. Participants will explore how these tools can help organize, analyze, and summarize survey responses, internal documents, reports, and other text-based information. The session will emphasize accessible workflows that can support decision-making, communication, and a deeper understanding of community needs. The final hour of the session will focus on curating and managing the data through APIs.  

Participants will explore how these tools can help them organize, analyze, and summarize information from sources such as:

  • Open-ended survey responses
  • Internal documents and administrative records
  • Meeting or interview notes
  • Community feedback
  • Grant-related materials
  • Other text-based information

A brief baseline survey will be administered before the session.  Participants may be eligible to earn UMBC microcrodential badges.

Session 5:  Large Language Models and Effective Prompting Practices

Format: UMBC – Public Policy Building, Room 451
Type: Interactive, lab-oriented
Date: Monday, Aubust 31, 2026
Time: 10:30am-2pm
Speakers: Dr. Lara Martin and Dr. Eric Stokan

Description:

Many organizations collect valuable feedback through surveys, focus groups, interviews, program notes, and community conversations but lack an efficient process for analyzing that information. This session will introduce participants to effective prompting practices and responsible workflows for using large language models to support qualitative and text-based analysis.

Participants will learn how to:

  • Write clear and effective prompts
  • Provide appropriate context and instructions to an AI model
  • Develop reusable prompt templates for common organizational tasks
  • Protect confidential or personally identifiable information
  • Determine when AI should—and should not—be used

Participants are being asked to bring their own data and interests to this final session.  Please feel free to share these ideas with socialscience@umbc.edu in advance of the session.

A final survey will be administered at the conclusion of the session. Participants will also receive information about related training and programming opportunities available on campus.

A brief baseline survey will be administered before the session.  Participants may be eligible to earn UMBC microcrodential badges.

 

CS3 sponsored events are open for full participation by all individuals regardless of race, color, religion, sex, national origin, or any other protected category under applicable federal law, state law, and the University’s nondiscrimination policy.