RT info:eu-repo/semantics/article
T1 Predicción Temprana del Abandono y Desempeño en el Examen Final en una Asignatura de Estadística en Línea
A1 Figueroa-Cañas, Josep
A1 Sancho-Vinuesa, Teresa
K1 Dropout prediction
K1 performance prediction
K1 decision trees
K1 quiz completion
K1 online university education
AB Higher education students who either donot complete the courses they have enrolled on orinterrupt their studies indefinitely remain a majorconcern for practitioners and researchers. Within eachcourse, early prediction of student dropout helpsteachers to intervene in time to reduce dropout rates.Early prediction of course achievement helps teacherssuggest new learning materials aimed at preventing atrisk students from failing or not completing the course.Several machine learning techniques have been used toclassify or predict at-risk students, including tree-basedmethods, which, though not the best performers, areeasy to interpret. This study presents two procedures foridentifying at-risk students (dropout-prone and nonachievers) early on in an online university statisticscourse. These enable us to understand how classifierswork. We found that student dropout and courseperformance prediction was only determined by theirperformance in the first half of the formative quizzes.Nevertheless, other elements of participation on thevirtual campus were initially considered. The classifierswill serve as a reference for intervention, despite theirmoderate performance metrics.
YR 2020
FD 2020
LK http://riull.ull.es/xmlui/handle/915/40184
UL http://riull.ull.es/xmlui/handle/915/40184
LA es
DS Repositorio institucional de la Universidad de La Laguna
RD 23-dic-2024