Using Generative AI-based Agents as External Regulating Agents to Measure and Foster Self-Regulated Learning Across Advanced Learning Technologies

Tuesday, February 20, 2024 noon to 1 p.m.

Go beyond reality, past imagination and unleash the possible with IST/School of Modeling, Simulation and Training during the next seminar in our series INSPIRING THE FUTURE.

Title: Using Generative AI-based Agents as External Regulating Agents to Measure and Foster Self-Regulated Learning Across Advanced Learning Technologies

Speaker: Dr. Roger Azevedo, University of Central Florida

When: Tuesday, February 20, 2024 

Time: 12:00 pm - 1:00 pm

Location: Partnership III, Room 233

Abstract: This talk introduces a groundbreaking approach to assess self-regulated learning (SRL) in STEM using generative AI-based agents as external regulating agents. Employing advanced learning technologies, these agents dynamically interact with learners within STEM tasks, domains, and problems while using different ALTs, capturing real-time data on cognitive, affective, metacognitive, and motivational processes. The generative AI models facilitate the detection, measurement, modeling, and inferences about SRL by analyzing learners' SRL behaviors, responses, engagement patterns, and decision-making in diverse STEM scenarios with different ALTs. The talk aims to demonstrate the effectiveness of this innovative method for comprehensive SRL assessment, providing valuable insights into learners' competency and informing the design of adaptive instructional strategies tailored to individual needs across various technological learning environments. 

Speaker Bio: Dr. Azevedo is a Professor in the School of Modeling Simulation and Training at the University of Central Florida. He is also an affiliated faculty in the Departments of Computer Science and Internal Medicine at the University of Central Florida and the lead scientist for the Learning Sciences Faculty Cluster Initiative. His main research area includes examining the role of cognitive, metacognitive, affective, and motivational self-regulatory processes during learning with advanced learning technologies (e.g., intelligent tutoring systems, simulations, serious games, immersive virtual learning environments). His overarching research goal is to understand the complex interactions between humans and intelligent learning systems by using interdisciplinary methods to measure cognitive, metacognitive, emotional, motivational, and social processes and their impact on learning, performance, and transfer. He has published over 300 peer-reviewed papers, chapters, and refereed conference proceedings. He was the former editor of the Metacognition and Learning journal and serves on the editorial board of several top-tiered learning and cognitive sciences journals (e.g., Applied Cognitive Psychology, International Journal of AI in Education, Educational Psychology Review, Learning & Instruction, Learning and Individual Differences, European Journal of Psychological Assessment). His research is funded by the National Science Foundation (NSF), Institute of Education Sciences (IES), National Institutes of Health (NIH), Army Research Lab, European Association for Research on Learning and Instruction (EARLI), and the Jacobs Foundation. He is a fellow of the American Psychological Association and the recipient of the prestigious Early Faculty Career Award from the National Science Foundation.

The Inspiring the Future: SMST Seminar Series is a series of regular 1-hour talks given throughout each semester, where preeminent researchers share their work with a highly interdisciplinary audience that includes students, faculty, military personnel, and industry leaders. The seminar series focuses on innovative modeling, simulation, and human-subjects research techniques.

Read More

Location:

Partnership III Building: 233

Contact:


Calendar:

Institute for Simulation & Training

Category:

Speaker/Lecture/Seminar

Tags:

Advanced Learning Technologies SelfRegulated Learning STEM Intelligent Tutoring Systems Generative AIbased Agents