New project to use AI to improve education


Students often struggle to estimate how well they know a subject, which can lead to ineffective learning or suboptimal academic achievement. A new project led by Associate Professor Dong Wang and Assistant Professor Nigel Bosch at the School of Information Studies at the University of Illinois at Urbana-Champaign aims to improve students’ ability to estimate their knowledge at using artificial intelligence (AI) methods. The researchers recently received a three-year, $850,000 grant from the National Science Foundation (NSF) for their project, “A Metacognitive Calibration Intervention Powered by Equitable and Private Machine Learning.”

“University students are often expected to do a considerable amount of study and learning outside of class hours, especially in online courses, which requires a high degree of self-regulation and metacognitive knowledge to study effectively,” Bosch said. “However, there are few opportunities to specifically learn self-regulation and metacognitive skills, particularly at the start of classes, when there is still time to improve study skills before major assessments (such as finals).”

“While there is a rich body of research on AI methods in educational settings, these efforts rarely consider some of the key social and human factors, such as privacy and fairness, that are necessary for learning. ‘widespread adoption of personalized educational software,’ Wang added. “This project addresses these issues with a new decentralized AI framework that is specifically aimed at educational settings.”

For their project, the researchers will use the predictive power of machine learning to anticipate undergraduate student performance in a course. Then they will teach students to recognize their trajectory while there is still time to improve it.

“For example, we might discover after a few weeks of a course that we can predict that a student is likely to get a C+ on an upcoming test, while the student might think they are on the right track. for an A,” Bosch said. “We will provide students with exercises to self-assess and improve their ability to assess their own learning, so they can better prioritize and motivate their study strategies.”

The AI ​​systems being developed will not directly access student data, to reduce bias related to key aspects of student identity. By improving AI “fairness” in this privacy-focused situation, student information cannot be directly used to audit or adjust models. According to the researchers, the privacy and fairness capabilities of the project framework will transform online post-secondary learning.

“This project will advance AI research by incorporating, for the first time, both a strict privacy safeguard for student data and equity considerations across multiple student demographics,” Wang said. . “It will also advance educational research in determining the effectiveness of preventive feedback in improving knowledge estimation skills and examining the mechanism by which this estimation influences educational outcomes.”

Wang’s research interests lie in the areas of human-centric AI, social sensing and intelligence, big data analytics, disinformation detection, and cyber-physical systems. humans. He holds a Ph.D. in computer science from the University of Illinois at Urbana-Champaign.

Bosch holds a cross-appointment in the Department of Educational Psychology, College of Education, University of Illinois at Urbana-Champaign. His research focuses primarily on machine learning and human-computer interaction applications in education. He holds a doctorate in computer science from the University of Notre Dame.

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of press releases posted on EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.


Comments are closed.