Clustering Analysis for Automatic Certification of LMS Strategies in a University Virtual Campus
In recent years, the use of Learning Management Systems (LMS) has grown considerably. This has had a strong effect on the learning process, particularly in higher education. Most universities incorporate LMS as a complement to face-to-face classes in order to improve the student learning process. Ho...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2019 |
| País: | España |
| Institución: | Universidad de Valladolid |
| Repositorio: | UVaDOC. Repositorio Documental de la Universidad de Valladolid |
| OAI Identifier: | oai:uvadoc.uva.es:10324/65502 |
| Acceso en línea: | https://doi.org/10.1109/ACCESS.2019.2943212 https://uvadoc.uva.es/handle/10324/65502 |
| Access Level: | acceso abierto |
| Palabra clave: | Data mining Education Tools Clustering methods Feature extraction Learning systems Machine learning |
| Sumario: | In recent years, the use of Learning Management Systems (LMS) has grown considerably. This has had a strong effect on the learning process, particularly in higher education. Most universities incorporate LMS as a complement to face-to-face classes in order to improve the student learning process. However, not all teachers use LMS in the same way and universities lack the tools to measure and quantify their use effectively. This study proposes a method to automatically classify and certify teacher competence in LMS from the LMS data. Objective knowledge of actual LMS use will help the university and its faculty to make strategic decisions. The information produced will be used to support teachers and institutions in the classification and design of courses by showing the different LMS usage patterns of teachers and students. In this study, we processed the structure of 3,303 courses and two million interactive events to obtain a classification model based on LMS usage patterns in blended learning. Three clustering methods were compared to find which one was best suited to our problem. The resulting model is clearly related to different course archetypes that can be used to describe the actual use of LMS. We also performed analyses of prediction accuracy and of course typologies across course attributes (academic disciplines and level and academic performance indicators). The results of this study will be used as the basis for an automatic expert system that automatically certifies teacher competence in LMS as evidenced in each course. |
|---|