Volume 4, 2026 – Issue 1
Attention and academic performance: AI-driven prediction and intervention
Elias Souza Ribeiro 
1 * and Carlos Eduardo Batista de Sousa 2
Laboratory of Cognition and Language (LCL), State University of Northern Rio de Janeiro (UENF), Campos dos Goytacazes, Brazil
Corresponding author: elias@ribeiroelias.com.br
DOI: 10.5281/zenodo.18839684
Abstract
Generational changes in cognitive performance and recent results from large-scale educational assessments have renewed interest in attention as a key factor in learning outcomes, particularly in the Brazilian context. This study investigates the role of focused, sustained, alternating, and divided attention in learning and presents an exploratory, performance-based digital assessment tool integrated with an artificial intelligence (AI)–assisted interpretative system to support educational research and decision-making. The system was developed using .NET MAUI and applied to a sample of 144 undergraduate students from Universidade Estadual do Norte Fluminense Darcy Ribeiro (UENF). Teachers provided qualitative ratings of student engagement and academic performance. The AI component, named Samantha, was designed to interpret attentional profiles and generate context-sensitive feedback for educators based on predefined psychometric and neuroscientific principles. Results showed weak positive associations between student engagement and both focused and sustained attention. An inverse association was observed between sustained attention and teacher-rated academic performance. This unexpected pattern should be interpreted cautiously and is treated as exploratory, given the study design and analytical constraints. Overall, the iGnosi® application demonstrated operational stability and practical usability during data collection. While not intended as a validated diagnostic instrument, the system represents a feasible framework for exploratory investigation of attentional patterns in educational settings and provides clear directions for future psychometric validation and controlled empirical testing.
Keywords: artificial intelligence, attention, education, academic performance, cognitive skills, ai intervention, predictive analytics
Published
2026/02/28
—
Section
Research Papers
How to Cite (APA)
Download Citation: EndNote/Zotero/Mendeley (RIS)
References
Anderson, B. A. (2016). The attention habit: how reward learning shapes attentional selection. Annals of the New York Academy of Sciences, 1369(1), 24–39. https://doi.org/10.1111/nyas.12957
Barbetta, P. A. (2012). Estatística aplicada às Ciências Sociais (P. R. da Silva, Ed.; 8th ed.). Editora UFSC.
Bauer, V. B. (2021). Neuropsicologia da aprendizagem em funções executivas e atenção. In Políticas e estratégias educacionais. Mérida Publishers. https://doi.org/10.4322/mp.978-65-994457-6-7.c3
Brasil. (2020). Brasil no Pisa 2018. INEP/MEC. https://www.gov.br/inep/pt-br/areas-de-atuacao/avaliacao-e-exames-educacionais/pisa/resultados
Carvalho, I. P., Costa, A., Silva, S., Moreira, B., Almeida, A., Moreira-Rosário, A., Guerra, A., Peixoto, B., Delerue-Matos, C., Sintra, D., Pestana, D., Pinto, E., Mendes, F. de C., Martins, I., Leite, J. C., Caldas, J. C., Fontoura, M., Maia, M. L., Queirós, P., … Calhau, C. (2020). Children’s performance on Raven’s Coloured progressive matrices in Portugal: The Flynn effect. Intelligence, 82. https://doi.org/10.1016/j.intell.2020.101485
D’Ambrósio, U. (2005). Sociedade, cultura, matemática e seu ensino. Educação e Pesquisa, 31(1), 99–120. https://doi.org/10.1590/S1517-97022005000100008
Flynn, J. R. (1984). The mean IQ of Americans: Massive gains 1932 to 1978. Psychological Bulletin, 95(1), 29–51. https://doi.org/10.1037/0033-2909.95.1.29
Flynn, J. R. (1987). Massive IQ gains in 14 nations: What IQ tests really measure. Psychological Bulletin, 101(2), 171–191. https://doi.org/10.1037/0033-2909.101.2.171
Flynn, J. R., & Shayer, M. (2018). IQ decline and Piaget: Does the rot start at the top? Intelligence, 66, 112–121. https://doi.org/10.1016/j.intell.2017.11.010
Júnior, A. G. (2018). ATENÇÃO E ENGAJAMENTO DISCENTE EM SITUAÇÕES DE SALA DE AULA ATTENTION AND STUDENT ENGAGEMENT IN THE CLASSROOM. Revista Habitus: Revista Da Graduação Em Ciências Sociais Do IFCS/UFRJ, 15(2), 46–62. https://revistas.ufrj.br/index.php/habitus
Marturano, E. M., Carla, L., & Elias, S. (2016). Família, dificuldades no aprendizado e problemas de comportamento em escolares. Educar Em Revista, 59, 123–139. https://doi.org/10.1590/0104-4060.44617
Moura, L. T., & Silva, K. P. M. (2019). O Transtorno de Déficit de Atenção e Hiperatividade (TDAH) e as práticas pedagógicas em sala de aula. Revista Eletrônica Acervo Saúde, 22, e216–e216. https://doi.org/10.25248/REAS.E216.2019
OCDE. (2023). NOTA SOBRE O BRASIL NO PISA 2022 DIRETORIA DE AVALIAÇÃO DA EDUCAÇÃO BÁSICA DAEB. INEP.
OCDE. (2025, May). Matriz de Ciências do PISA 2025. https://pisa-framework.oecd.org/science-2025/bra_por/
Oliveira, P. V. de, Muszkat, M., & Fonseca, M. F. B. C. da. (2019). Relação entre índice de motivação escolar e desempenho acadêmico de crianças com transtorno de déficit de atenção/hiperatividade e grupo controle. Revista Psicopedagogia, 36(109), 24–33. http://pepsic.bvsalud.org/scielo.php?script=sci_arttext&pid=S0103-84862019000100004&lng=pt&nrm=iso&tlng=pt
OpenAI. (2024). Fine-tuning – OpenAI API. https://platform.openai.com/docs/guides/fine-tuning
Rabelo, I. S., Cruz, R., & Castro, N. R. De. (2020). BATERIA ROTAS DE ATENÇÃO Rota da Atenção Concentrada (Rota C) Rota da Atenção Dividida (Rota D) Rota da Atenção Alternada (Rota A) MANUAL TÉCNICO (I. B. Guntert, Ed.; 1st ed.). NilaPress.
Ribeiro, E. S., & Sousa, C. E. B. de. (2025). SAMANTHA: IA APLICADA AO ESTUDO DA RELAÇÃO ENTRE ATENÇÃO E APRENDIZAGEM. Revista Interinstitucional Artes de Educar, 11(1), 245–261. https://doi.org/10.12957/RIAE.2024.86267
Rueda, F. J. M. (2013). Bateria Psicológica para Avaliação da Atenção – BPA (Vol. 1). Vetor.
Sassaki, A. H., Di Pietra, G. A. C., Filho, N. A. M., & Komatsu, B. K. (2018). Por que o Brasil vai Mal no PISA? Uma Análise dos Determinantes do Desempenho no Exame. INSPER. https://www.researchgate.net/publication/326718184
Sharpe, M. J., & Killcross, S. (2015). The prelimbic cortex directs attention toward predictive cues during fear learning. Learning & Memory, 22(6), 289–293. https://doi.org/10.1101/lm.038273.115
Shayer, B., Carvalho, C., Mota, M., Argollo, N., Abreu, N., & Bueno, O. F. A. (2015). Desempenho de escolares em atenção e funções executivas no Nepsy e inteligência. Revista Psicologia: Teoria e Prática, 17(1), 120–135. https://doi.org/10.15348/1980-6906/psicologia.v17n1p120-135
Teasdale, T. W., & Owen, D. R. (2008). Secular declines in cognitive test scores: A reversal of the Flynn Effect. Intelligence, 36(2), 121–126. https://doi.org/10.1016/J.INTELL.2007.01.007
About the authors
- Elias Souza Ribeiro is a researcher in neuroeducation and cognitive assessment. He holds an M.Sc. in Natural Sciences from Universidade Estadual do Norte Fluminense (UENF), where he investigated attentional processes and learning outcomes using iGnosi®, a cross-platform psychometric instrument he developed and integrated with a custom-trained artificial intelligence model. His research focuses on attention, executive functions, computational psychometrics, and the use of AI-driven tools to support educational evaluation and evidence-based decision-making in learning environments.
elias@ribeiroelias.com.br
↩︎ - Carlos Eduardo Batista de Sousa is an Associate Professor of Philosophy, Laboratory of Cognition and Language, UENF. PhD in Philosophy (Epistemology) from the University of Konstanz, Germany, Master’s and Bachelor’s degrees in Philosophy from UFRJ. Research areas: General Epistemology, Philosophy and Theory of Science, Neurophilosophy and Philosophy of Neuroscience, Philosophy of Physics and Psychophysics. Research focuses on the brain/consciousness relationship, the nature of matter, and the foundations of the Natural Sciences. Additional interests include Theoretical Rationality, Philosophy of Language and Mind, Logic, and Metaphysics.
cdesousa@uenf.br
↩︎
