Learning Outside the Classroom During a Pandemic: Evidence from an Artificial Intelligence-Based Education App.

This article investigates how K-12 students compensate for learning loss during the COVID-19 pandemic through the use of an artificial intelligence (AI)-powered math education app called QANDA. Focusing on a tripartite perspective of compensatory behavior—quantity (volume of app use), pattern (regularity of use), and pace (progression through the curriculum)—the study compares students living in the pandemic epicenter region of Daegu and Gyeongbuk (DG) in South Korea with those in other regions. Findings reveal that students in the epicenter initially reduced app usage and fell behind in the curriculum but subsequently increased usage more than others, adopted a more uniform study pattern, and caught up in curriculum pace, demonstrating compensatory learning behavior. Additionally, the proximity of a goal, such as the national university entrance exam, partially moderated these effects, with high school students showing faster and greater recovery than middle school students. The research highlights the role of AI-powered educational technologies in facilitating learning recovery during crises and offers implications for educators, EdTech developers, and policymakers.