Multi-agentes con aprendizaje automático en el proceso de morfosintaxis
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Edu. Sup. Rev. Cient. Cepies
Abstract
El artículo aborda el desarrollo de un modelo de sistema multi-agente con aprendizaje automático para optimizar el proceso de enseñanza de la morfosintaxis en los estudiantes de Seminario de Grado I en la Carrera de Economía de la Universidad Mayor de San Andrés. Mediante la integración de técnicas de inteligencia artificial y un enfoque colaborativo entre agentes, se busca mejorar significativamente la comprensión y aplicación de las reglas morfosintácticas. El modelo no solo facilita la personalización del aprendizaje, sino que también promueve la eficiencia en la enseñanza de la gramática, contribuyendo al rendimiento académico de los estudiantes. Los agentes inteligentes, como el agente tutor y el agente evaluador, permiten una adaptación individualizada a las necesidades de los estudiantes, ofreciendo una retroalimentación constante y oportuna. El Deep Learning en la misma arquitectura del sistema multi-agente refuerza el proceso de aprendizaje, lo que permite una interacción más efectiva entre los agentes y los estudiantes. El artículo concluye que el modelo propuesto, basado en la metodología MASE y ofrece resultados significativos que pueden ser adaptados a otros contextos educativos. La evaluación del modelo mediante encuestas indica una mejora notable en el proceso de enseñanza-aprendizaje de la morfosintaxis, con una calificación favorable por parte de los estudiantes. Esta investigación destaca el potencial de los sistemas multi-agente con aprendizaje automático como herramientas clave en la educación superior, particularmente en áreas donde la gramática y la estructura del lenguaje son fundamentales.
The article addresses the development of a multi-agent system model with machine learning to optimize the teaching process of morphosyntax in Grade I Seminar students in the Economics Program at the Universidad Mayor de San Andrés. By integrating artificial intelligence techniques and a collaborative approach between agents, the aim is to significantly improve the understanding and application of morphosyntactic rules. The model not only facilitates the personalization of learning, but also promotes efficiency in teaching grammar, contributing to students' academic performance. Intelligent agents, such as the tutor agent and the evaluator agent, allow individualized adaptation to the needs of students, offering constant and timely feedback. Deep Learning in the same architecture of the multi-agent system reinforces the learning process, allowing a more effective interaction between agents and students. The article concludes that the proposed model, based on the MASE methodology and offers significant results that can be adapted to other educational contexts. The evaluation of the model through surveys indicates a notable improvement in the teaching-learning process of morphosyntax, with a favorable rating from the students. This research highlights the potential of multi-agent systems with machine learning as key tools in higher education, particularly in areas where grammar and language structure are fundamental.
The article addresses the development of a multi-agent system model with machine learning to optimize the teaching process of morphosyntax in Grade I Seminar students in the Economics Program at the Universidad Mayor de San Andrés. By integrating artificial intelligence techniques and a collaborative approach between agents, the aim is to significantly improve the understanding and application of morphosyntactic rules. The model not only facilitates the personalization of learning, but also promotes efficiency in teaching grammar, contributing to students' academic performance. Intelligent agents, such as the tutor agent and the evaluator agent, allow individualized adaptation to the needs of students, offering constant and timely feedback. Deep Learning in the same architecture of the multi-agent system reinforces the learning process, allowing a more effective interaction between agents and students. The article concludes that the proposed model, based on the MASE methodology and offers significant results that can be adapted to other educational contexts. The evaluation of the model through surveys indicates a notable improvement in the teaching-learning process of morphosyntax, with a favorable rating from the students. This research highlights the potential of multi-agent systems with machine learning as key tools in higher education, particularly in areas where grammar and language structure are fundamental.
Description
Vol. 11, No. 2