Differentiated impacts of GenAI-supported self-regulated game-based science learning: a behavioural and epistemic network analysis of high- and low-achieving students

This research explores the differentiated impacts of Generative Artificial Intelligence (GenAI) integration into digital game-based learning (DGBL) environments, specifically focusing on self-regulated learning (SRL) for junior high school students with varying academic achievements. The study investigates how GenAI-supported self-regulated DGBL influences learning motivation, behavioral patterns, perceptions, and prompt usage within a physics context.

Why it matters

The integration of advanced AI, such as GenAI, into educational technologies represents a significant evolution in personalized learning approaches, offering scalable methods to enhance student engagement and outcomes. Understanding its differentiated impacts across various student demographics is crucial for informing future educational technology development and policy, ensuring equitable and effective deployment.

Key insights

• GenAI integration in digital game-based learning offers new opportunities for enhancing student learning through personalized support, immediate feedback, and adaptive interaction.
• Previous research has explored GenAI effectiveness in education, but there is limited study on its role in supporting self-regulated learning within game-based science environments.
• The study specifically examines the impact of GenAI-supported self-regulated digital game-based learning (GenAI-SRDGBL) on junior high students.
• The analysis considers students across different academic achievement levels.
• Key areas of investigation include learning motivation, behavioral patterns, student perceptions, and the utilization of GenAI prompts.

Source

Educational Technology Research and Development — https://link.springer.com/article/10.1007/s11423-026-10709-9