Sistema recomendador de ejercicios para el desarrollo de habilidades de pensamiento computacional
Cargando...
Archivos
Fecha
2021
Autores
Profesor/a Guía
Facultad/escuela
Idioma
es
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Andrés Bello
Nombre de Curso
Licencia CC
Licencia CC
Resumen
El desarrollo de la sociedad va ligado al desarrollo de las personas que la
componen, es así como los humanos necesitan progresar aprendiendo tanto de
literatura como también de matemáticas. En el mundo actual se agrega el
aprendizaje del pensamiento computacional, para poder entender la tecnología
y usarla para obtener resultados de una forma clara y sencilla a los problemas
de la vida diaria.
Este experimento busca apoyar a los estudiantes para lograr un desarrollo de las
habilidades del pensamiento computacional mediante un análisis realizado a
estudiantes de la universidad Andrés Bello en el ramo de programación. Así se
construye un dashboard que utiliza la información de cada uno de los estudiantes
para poder observar y comparar las habilidades que estos desarrollan.
Para apoyar al estudiante en el aprendizaje y considerando las diferencias entre
ellos, es que se diseña un sistema recomendador que permita que al alumno se
le sugiera un ejercicio a realizar, que le brinde el mayor conocimiento requerido
de acuerdo a su situación académica actual.
Utilizando herramientas y algoritmos de machine learning se logra obtener dos
tipos de sistemas recomendadores los cuales tienen distintos focos para realizar
la recomendación. Los sistemas de recomendación se generaron en base a los
datos del estudiante, tales como la cantidad de ejercicios que realizó, la nota final
que este obtuve, la cantidad de veces que se realizó un ejercicio en particular,
etc.
Esto demuestra que se puede generar un sistema recomendador de ejercicios
para los estudiantes que apoye el desarrollo del pensamiento computacional y
que también no existe una única forma de recomendar, sino que todo depende
de los datos que se utilicen, cómo se utilicen y los objetivos que se deseen lograr.
The development of society is linked to personal development, this is how humans need to progress by learning both literature and mathematics. In a digital society its necessary to develop computational thinking skills, in order to fully understand the technology and learn to use it to obtain results in a clear and simple way to find solutions to everyday problems. This experiment seeks to support students to achieve a development of computational thinking skills through an analysis that is made to students of the Andrés Bello University enrolled in a programming course. A dashboard is built that uses the information of each of the students to allow the teacher to be able to observe and compare the skills that they develop. To support the student in learning and not only allowing to see the differences with other students, a recommendation system is designed. The system allows to recommended to the students an exercise (programming task) to perform which provides the maximum benefit to them. Using machine learning tools and algorithms, we obtain two recommender systems which have different mechanisms to make the recommendation. The recommendation systems which are generated are based on student's data, such as the number of exercises the student performs, the final grade that the student obtains, the number of times a particular exercise is performed, etc. This shows that an exercise recommender system can be generated for students that supports the development of computational thinking and that there is also not only a way to recommend, but that everything depends on the data that is used, how it is used and the objectives of the study.
The development of society is linked to personal development, this is how humans need to progress by learning both literature and mathematics. In a digital society its necessary to develop computational thinking skills, in order to fully understand the technology and learn to use it to obtain results in a clear and simple way to find solutions to everyday problems. This experiment seeks to support students to achieve a development of computational thinking skills through an analysis that is made to students of the Andrés Bello University enrolled in a programming course. A dashboard is built that uses the information of each of the students to allow the teacher to be able to observe and compare the skills that they develop. To support the student in learning and not only allowing to see the differences with other students, a recommendation system is designed. The system allows to recommended to the students an exercise (programming task) to perform which provides the maximum benefit to them. Using machine learning tools and algorithms, we obtain two recommender systems which have different mechanisms to make the recommendation. The recommendation systems which are generated are based on student's data, such as the number of exercises the student performs, the final grade that the student obtains, the number of times a particular exercise is performed, etc. This shows that an exercise recommender system can be generated for students that supports the development of computational thinking and that there is also not only a way to recommend, but that everything depends on the data that is used, how it is used and the objectives of the study.
Notas
Tesis (Ingeniero Civil Informático)
Palabras clave
Pensamiento Computacional, Tecnología Educativa