º£½ÇÉçÇø

As a computer science researcher, my work focuses on advancing AI for Good, civic technology and human-centered computing to strengthen how communities learn, collaborate, and access opportunities. My research integrates AI-augmented inquiry-based learning, data visualization, learning analytics, and network science to design tools that democratize data, improve educational equity, and support public-benefit ecosystems. As PI of the SIPA-funded RILE Connect project, I am committed to building accessible digital infrastructures and responsible AI systems that empower diverse learners, educators, and communities.

C3 Lab: Community-Centered Computing Lab

The Community-Centered Computing Lab (C3 Lab) is co-directed by Dr. Daniel Pittman and Dr. Ranjidha Rajan. The lab supports research and development projects that create technology for communities, including statewide data platforms, conversational AI systems, STEM ecosystem tools, and campus engagement applications. Our mission is to design and deploy computing systems that empower communities by improving access to information, strengthening decision-making, and enabling human centered interaction with data and AI tools.

Our work emphasizes human centered computing, applied AI, LLM-driven interfaces, data engineering, geospatial integration, and accessible design. Students in the C3 Lab work on production software systems, contribute to federal and state funded research, and help build platforms that directly benefit Colorado communities and º£½ÇÉçÇø.

The lab’s current research initiatives include:

• The Colorado Sustainability Hub, a statewide sustainability-data platform integrating AI, geospatial systems, and natural language interaction
• RILE Connect, a statewide STEM mentorship and opportunity-matching platform
• Roadrunner Connect, a student-built mobile and web application supporting º£½ÇÉçÇø’s campus community

Together, these projects form the core applied research portfolio of the C3 Lab and reflect our mission to develop human centered, community responsive computing systems that serve statewide and institutional needs.

1) RILE Connect: Colorado STEM Ecosystem Platform- Funded by the Colorado SIPA GovGrants Program

I am honored to serve as the Principal Investigator and Project Director for the RILE Connect project, an innovative digital ecosystem initiative funded by the Colorado Statewide Internet Portal Authority (SIPA) for $495,922. The award was granted on November 7, 2025, and project work will begin in Spring 2026. Student researchers in the C3 Lab will help design and develop the RILE Connect platform, contributing to front-end and mobile development, cloud infrastructure, API integration, and data-driven matching workflows. This project builds a statewide, publicly accessible STEM collaboration platform designed to connect K–12 schools, higher education institutions, nonprofits, and industry partners across Colorado. The system strengthens access to opportunities, mentoring networks, internships, and high-impact learning experiences, providing a rich ecosystem for student success and equity-focused workforce development.

RILE Connect advances data democracy, network transparency, and STEM accessibility by enabling stakeholders to discover collaboration pathways, visualize partnership networks, and engage in co-defined regional projects. As PI, I lead technical architecture, platform development, and ecosystem analytics. Students who join this project learn to build real-world systems that directly impact Colorado’s statewide STEM pipeline.

Student Involvement Areas:

Web and Mobile application development, Database design and optimization, Network visualization, User experience design (UI/UX prototyping), Data dashboards for ecosystem insights, Community partner mapping and analysis, Building recommendation system.

2) MentorMap: Network-Driven Mentorship Analysis & Visualization

MentorMap leverages social network analysis and graph database technologies to model, query, and visualize mentorship ecosystems across academic, professional, or community settings. Using tools like Neo4j, ArangoDB, or Amazon Neptune, the system represents participants as nodes and mentorship ties as edges, enriched with attributes such as expertise areas, engagement frequency, demographics, and program affiliation. Students use graph queries to uncover central mentors, multi-layer mentorship chains, communities of practice, and structural gaps in support networks. By combining graph database analytics with interactive visualization, MentorMap reveals how mentorship flows through an ecosystem and identifies opportunities to strengthen access, equity, and matching strategies.

Student Involvement Areas

Graph Database Modeling & Querying, Graph Analytics & Visualization, Insight Generation for Programs.

3) Canvas Learning Analytics & Course Engagement Dashboards- Data-Driven Insights for Student Success

This project analyzes learning management system activity logs to model student engagement patterns, assignment behaviors, resource usage, and weekly learning rhythms. By integrating descriptive analytics with machine learning concepts—such as clustering, classification, and time-series pattern detection, the project generates insights that support early alerts, instructional redesign, and equitable teaching practices. The goal is to help instructors understand who is engaging, how they are navigating the course, and where intervention may be needed.

Student Involvement Areas

Data cleaning and preprocessing of clickstream logs, timestamps, and event data, exploring engagement clusters , identifying behavioral patterns, building dashboards, analyzing assignment submission trends, applying predictive modeling concepts, Investigating fairness and equity by comparing engagement patterns across student groups.

4) AI-IBL for Scaffolded Data Questioning in Data Visualization

Helping Students Learn to Ask Better Data Questions.

This initiative focuses on how generative AI can help students practice deeper, more meaningful questioning during exploratory data analysis (EDA). The work analyzes how AI-influenced questioning compares with human inquiry patterns and how scaffolds improve students’ data literacy.

Student Involvement Areas

Developing EDA notebooks in Python, analyzing human vs. AI-generated data questions, designing metacognitive reflection tasks, running small-scale experiments in visualization classes, creating example dashboards that support data questioning.

Please email [email protected] if you are interested in any of these or for more information.