RESUMENLa apreciación del estado cognitivo de un estudiante presenta inconvenientes originados en el tratamiento de la imprecisión presente tanto en la naturaleza dinámica del estado cognitivo así como en el enfoque interpretativo de la evaluación del educador. La valoración del desempeño con una puntuación rígida aparece como inapropiada para medir este fenómeno dinámico. A fin de mejorar el diagnóstico cognitivo, se propone un modelo de evaluación basado en lógica difusa. El modelo está compuesto por 27 reglas difusas que capturan la experticia de los profesores y utiliza tres variables lingüísticas de entrada y una de salida. La experiencia realizada mostró una visión mejorada del diagnóstico cognitivo con la obtención de información adicional a partir de las notas tradicionales. Las ventajas encontradas comprenden la obtención de una mayor flexibilidad en la evaluación con respecto a la rígida evaluación tradicional y la posibilidad de que los docentes puedan expresarse en lengua natural. Palabras clave: diagnóstico cognitivo, lógica difusa, experiencia docente, evaluación del estudiante Cognitive Diagnosis Model based on Fuzzy LogicThe appreciation of a student's cognitive status has problems originated in the treatment of the imprecision present in the nature of the cognitive status' dynamic. The interpretative focus of the observations done by the teacher on the student's activity also influences in the before mentioned problems. The assessment with a rigid scoring seems inappropriate to measure this dynamic phenomenon. In order to treat the imprecision involved in a more flexible way, an approach based on fuzzy logic is proposed aiming at improving the diagnosis. In this approach, the linguistic variable knowledge level is estimated using three linguistic variables: grades' progression, tests' passing level, and final grade with respect to the course's average. The approach is comprised by 27 fuzzy rules that capture the professors' expertise and uses three linguistic variables of input and one of output. The experience carried out showed an enlarged vision to obtain additional information from traditional grades. Advantages have been found in the students' assessment with the proposed approach: it is more flexible than the traditional assessment and the professors can express themselves in a natural language.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.