Wright State professor helping to develop AI learning environments

Noah Schroeder is professor of educational technology and instructional design in the Department of Leadership Studies in Education and Organizations.

Noah L. Schroeder, Ph.D., a professor of educational technology and instructional design at Wright State University, will be receiving a $400,000 grant as part of the AI Institute for Inclusive Intelligent Technologies for Education (INVITE).

The grant is part of a larger five-year $20 million award received jointly by ETS (Educational Testing Service), the University of Illinois Urbana-Champaign, Temple University and the University of Florida.

Led by the University of Illinois Urbana-Champaign, the institute seeks to fundamentally reframe how educational technologies geared toward teaching science, technology, engineering and math interact with learners by developing artificial intelligence tools and approaches to support three crucial noncognitive skills important to support learning: persistence, academic resilience and collaboration.

“One goal I’m really excited about is exploring the design factors that can support persistence, academic resilience and collaboration in these intelligent systems,” said Schroeder.

Institute research will revolve around three interconnected strands, including the collection, analysis, and sharing of novel datasets for fair and robust machine learning and natural language understanding; building novel, robust methods for understanding learner behaviors and persistent, integrated learner models that incorporate assessments of social and emotional skills; and developing new inclusive STEM learning environments that provide natural and adaptive interaction with socially aware pedagogical agents.

Schroeder, who joined the Wright State faculty in 2014, has broadly focused his research on the design of computer-based learning environments, and much of his work is around the design of pedagogical agents.

His research for the institute will primarily be in the third strand and will involve designing AI-driven pedagogical agents that help support students’ noncognitive skills. Pedagogical agents are characters within learning software that students interact with to help them learn.

“For example, a student might be learning about math and get something wrong while working their way through a problem,” said Schroeder. “At that point, a virtual character might pop up on the screen and help provide them an explanation of what they did wrong in the problem. Maybe it will ask them a question that will cause them to self-reflect on why they chose one answer rather than another.”

Schroeder said that designing a pedagogical agent and then integrating it into the learning system is not an easy thing to do because a lot of specialized skill sets go into it.

“You would need somebody to draw the character, animate the character, connect it to the text-to-speech software, someone to design the AI, and someone would need to bring all these pieces together so the agent actually works within the learning system. That’s a lot of technical skills for any one person to have,” he said. “We are working with a partner called Balance Studios to help us design a toolkit so that we can more easily create the virtual characters and then embed them into a variety of different learning systems. I’m going to be working with Balance Studios and other collaborators on the project to decide what types of things about the virtual characters should be editable in the toolkit.”

Schroeder said he is excited to work on such a large and comprehensive project and to have an opportunity to collaborate on such a large scale.

“I find it really exciting that we are bringing together all of these different skill sets to design intelligent systems to support noncognitive skills,” he said. “Opportunities like this don’t happen every day.”