Aprendizaje de análisis matemático mediante agentes inteligentes
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Edu. Sup. Rev. Cient. Cepies
Abstract
El artículo presenta un enfoque novedoso para mejorar el aprendizaje de Análisis Matemático mediante el uso de agentes inteligentes, integrados con el modelo de aprendizaje experiencial de Kolb. Este enfoque se centra en personalizar el proceso educativo, adaptándolo a los diferentes estilos de aprendizaje de los estudiantes, Kolb clasifica en activo, reflexivo, teórico y pragmático. Los agentes inteligentes actúan como tutores personalizados, proporcionando retroalimentación y guía en cada paso, lo que facilita una comprensión más profunda y duradera de los conceptos matemáticos en comparación con métodos tradicionales. El sistema pedagógico consta de cuatro módulos: interfaz, dominio, tutor y estudiante. Estos módulos se coordinan para monitorear el progreso de los estudiantes, identificar errores y ofrecer intervenciones necesarias para corregirlos, generando una experiencia de aprendizaje continuo y dinámico promoviendo así un ambiente interactivo y centrado en el estudiante. La investigación, realizada en estudiantes de Análisis Matemático I, revela que los estilos de aprendizaje predominantes en este grupo son el convergente y el asimilador, que coinciden bien con los requerimientos analíticos y lógicos de la materia. Los resultados muestran que los estudiantes que interactúan con el agente pedagógico obtienen mejores calificaciones y mayor satisfacción con el proceso de aprendizaje. El estudio concluye que la integración de agentes inteligentes puede transformar la educación universitaria, especialmente en disciplinas complejas. Esta tecnología tiene el potencial de ser implementada en otras áreas, promoviendo un aprendizaje personalizado que atienda las necesidades individuales de los estudiantes y mejore su desempeño académico, ampliando las posibilidades de una educación más adaptativa y eficaz.
The article presents a novel approach to improve the learning of Mathematical Analysis through the use of intelligent agents, integrated with Kolb's experiential learning model. This approach focuses on personalizing the educational process, adapting it to the different learning styles of students, Kolb classifies them as active, reflective, theoretical and pragmatic. Intelligent agents act as personalized tutors, providing feedback and guidance at every step, facilitating a deeper, longer-lasting understanding of mathematical concepts compared to traditional methods. The pedagogical system consists of four modules: interface, domain, tutor and student. These modules are coordinated to monitor student progress, identify errors and offer necessary interventions to correct them, generating a continuous and dynamic learning experience, thus promoting an interactive and student-centered environment. The research, carried out on Mathematical Analysis I students, reveals that the predominant learning styles in this group are convergent and assimilative, which coincide well with the analytical and logical requirements of the subject. The results show that students who interact with the pedagogical agent obtain better grades and greater satisfaction with the learning process. The study concludes that the integration of intelligent agents can transform university education, especially in complex disciplines. This technology has the potential to be implemented in other areas, promoting personalized learning that meets the individual needs of students and improves their academic performance, expanding the possibilities of a more adaptive and effective education.
The article presents a novel approach to improve the learning of Mathematical Analysis through the use of intelligent agents, integrated with Kolb's experiential learning model. This approach focuses on personalizing the educational process, adapting it to the different learning styles of students, Kolb classifies them as active, reflective, theoretical and pragmatic. Intelligent agents act as personalized tutors, providing feedback and guidance at every step, facilitating a deeper, longer-lasting understanding of mathematical concepts compared to traditional methods. The pedagogical system consists of four modules: interface, domain, tutor and student. These modules are coordinated to monitor student progress, identify errors and offer necessary interventions to correct them, generating a continuous and dynamic learning experience, thus promoting an interactive and student-centered environment. The research, carried out on Mathematical Analysis I students, reveals that the predominant learning styles in this group are convergent and assimilative, which coincide well with the analytical and logical requirements of the subject. The results show that students who interact with the pedagogical agent obtain better grades and greater satisfaction with the learning process. The study concludes that the integration of intelligent agents can transform university education, especially in complex disciplines. This technology has the potential to be implemented in other areas, promoting personalized learning that meets the individual needs of students and improves their academic performance, expanding the possibilities of a more adaptive and effective education.
Description
Vol. 11, No. 3