Project Activities
Focused program of research
INVITE research will pursue foundational AI advances in robust and fair machine learning, learner modeling, and natural language understanding to enable the assessment and modeling of noncognitive skill development over time and across domains. It will revolve around three interconnected strands:
- Collect, analyze, and share novel datasets for fair and robust machine learning and natural language understanding.
- Build novel, robust methods for understanding learner behaviors and persistent, integrated learner models that incorporate assessments of noncognitive skills.
- Develop new inclusive STEM learning environments that provide natural and adaptive interaction with socially aware pedagogical agents.
INVITE researchers will also fit interpretable generative models to real data and simulated learners to enable new discoveries and hypotheses about human learning.
Use-inspired research will focus on how learners communicate STEM content, how they learn to persist through challenging work, and how teachers support and promote noncognitive skill development. INVITE will integrate AI-based tools into classrooms to empower teachers to support learners in more developmentally appropriate ways. INVITE's work will generate a rich set of data documenting learners' interactions with educational technologies, each other, and teachers, allowing future researchers to study learner growth over time and across different STEM activities. INVITE's use-inspired research aims to advance the science of noncognitive skill acquisition during STEM learning and uncover relevant contextual aspects of learning historically overlooked by AI systems.
National leadership and outreach activities
INVITE will serve as a nexus for building capacity for research, education, and broadening participation in the intersection of AI and Education for All, serving a wide array of stakeholders. Specifically, the INVITE will
- produce a database of multimodal datasets for use by other researchers
- provide open-source tools and opportunities to develop knowledge about the use, control, and impact of innovative AI-enabled education systems
- actively build a diverse workforce of future scientists and engineers to design, implement, and deploy the next generation of AI-enabled Education for All systems.
INVITE's research and outreach activities will draw from the INVITE K-12 partner network reaching up to 96,000 learners across 24 school districts and nonprofits spanning 8 states. INVITE will offer inclusive programs to support diverse students' participation in research experiences, undergraduate courses in AI in education, and professional development programs for teachers.
Structured Abstract
Setting
The focused program of research will take place in the states of California, Florida, Illinois, New Jersey, New York, Oregon, Michigan, Pennsylvania, and Texas. Partnering schools and school districts are balanced between urban, suburban, and rural settings. Research will occur in classrooms and during homework-focused afterschool programs.
Sample
The sample will consist of students and teachers in grades 3 through 9 with an estimate of 3,000 students engaged in studies and data collection efforts over the life of the institute (31% Black or African American, 27% Hispanic or Latino/a, and 12% other historically underserved groups; with 67% of learners classified as low-income, and 16% English language learners). Approximately 50 teachers per year will be engaged in research and co-design activities, with an additional 350 total engaged in training/outreach.
People and institutions involved
IES program contact(s)
Supplemental information
Co-Principal Investigators: Boyer, Kristy; Payton, Jamie; Zapata, Diego; Zhai, ChenXiang
Questions about this project?
To answer additional questions about this project or provide feedback, please contact the program officer.
