EEG-Based Brain-Computer Interface for Educational Games: Cognitive State Monitoring in AI-Driven Financial Literacy Learning

• Gabriel Machado Santos UFU
• Rita Maria Silva Julia UFU
• Marcelo Zanchetta do Nascimento UFU

DOI: https://doi.org/10.5753/sbgames_estendido.2026.25261

Resumo

Introduction: Behavioral logs from educational games capture player actions but not the cognitive states underlying decisions. EEG complements these logs by providing continuous measures of attention and affect. Objective: We present a feasibility study integrating an Emotiv EPOC X (14-channel) EEG headset with a Unity 3D financial literacy game for two purposes: BCI-based game control through mental commands and passive monitoring of six cognitive metrics—Interest, Excitement, Stress, Engagement, Relaxation, and Attention—synchronized with AI advisor interventions. Methodology: We implemented a Unity–Emotiv Cortex SDK pipeline and evaluated six children in two sessions: a BCI Control Session, using four mental commands (Left, Right, Push, and Idle), and a Cognitive Monitoring Session, in which EEG metrics were passively synchronized with in-game AI advisor events. Results: Preliminary results show alignment between EEG-derived cognitive states, player decisions, and self-reports. Stress increased during gambling events and remained stable after investment decisions consistent with AI guidance, demonstrating the feasibility of integrating EEG into educational games and motivating future multimodal adaptive learning systems.

Palavras-chave: Brain Computer Interface, EEG, Educational Games, Financial Literacy, Cognitive State Monitoring, Adaptive Learning

Referências

Apicella, A., Arpaia, P., Frosolone, M., e Moccaldi, N. (2022). EEG-based measurement system for monitoring student engagement in learning 4.0. Scientific Reports, 12:5857.

Bellotti, F., Berta, R., De Gloria, A., e Primavera, L. (2009). Enhancing the educational value of video games. Computers in Entertainment, 7(2):1–18.

John and the Rainbow Coins Project (2026). John and the rainbow coins. [link].

Lotte, F., Congedo, M., Lécuyer, A., Lamarche, F., e Arnaldi, B. (2013). A review of classification algorithms for EEG-based brain-computer interfaces. Journal of Neural Engineering, 4(2):R1.

Machado Santos, G., Maria Silva Julia, R., e Zanchetta do Nascimento, M. (2026). Personalizing financial literacy learning for children through genai and agentic design: A game-based experiment. Expert Systems with Applications, 309:131149.

Müller, K.-R., Anderson, C. W., e Birch, G. E. (2003). Linear and nonlinear methods for brain-computer interfaces. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 11(2):165–179.

Pei, L., Jong, M. S.-Y., Shang, J., e Ouyang, G. (2025). Design and validation of an electroencephalogram-supported approach to tracking real-time cognitive load variations for adaptive video-based learning. British Journal of Educational Technology, 56:1553–1572.

Plass, J. L., Homer, B. D., e Kinzer, C. K. (2015). Foundations of game-based learning. Educational Psychologist, 50(4):258–283.

Ramirez, R. e Vamvakousis, Z. (2012). Detecting emotion from eeg signals using the emotive epoc device. In International Conference on Brain Informatics, pages 175–184. Springer.

VanLehn, K. (2011). The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems. Educational Psychologist, 46(4):197–221.