Journal Article

Early Prediction of Student Learning Performance Through Data Mining: A Systematic Review

Romero, Cristobal, Lara Torralbo, Juan, López-Zambrano, Javier

2021

Overview

Background: Early prediction of students' learning performance using data mining techniques is an important topic these days. The purpose of this literature review is to provide an overview of the current state of research in that area. Method: We conducted a literature review following a two-step procedure, looking for papers using the major search engines and selection based on certain criteria. Results: The document search process yielded 133 results, 82 of which were selected in order to answer some essential research questions in the area. The selected papers were grouped and described by the type of educational systems, the data mining techniques applied, the variables or features used, and how early accurate prediction was possible. Conclusions: Most of the papers analyzed were about online learning systems and traditional face-to-face learning in secondary and tertiary education; the most commonly-used predictive algorithms were J48, Random Forest, SVM, and Naive Bayes (classification), and logistic and linear regression (regression). The most important factors in early prediction were related to student assessment and data obtained from student interaction with Learning Management Systems. Finally, how early it was possible to make predictions depended on the type of educational system. Keywords: Educational Data Mining; Learning Analytics; Early prediction of academic performance; Early Warning Systems; Detection of students at-risk of Dropping-out. Prediccion Temprana del Rendimiento Academico con Mineria de Datos: una Revision Sistematica. Antecedentes: la prediccion temprana del rendimiento academico mediante tecnicas de mineria de datos es un campo de estudio emergente, que se pretende analizar por medio de este articulo de revision. Metodo: se ha revisado la literatura existente por medio de un proceso de busqueda de articulos en los principales motores de busqueda, y de seleccion de los mismos de acuerdo con ciertos criterios. Resultados: el proceso de busqueda reporto 133 resultados, de los cuales 82 fueron seleccionados para dar respuesta a las preguntas de investigacion planteadas. Se han agrupado los trabajos encontrados para poder dar respuesta a las preguntas por tipo de sistema educativo, tecnicas de mineria de datos aplicadas, variables empleadas y grado de anticipacion con el que se puede predecir. Conclusiones: la mayor parte de los trabajos publicados corresponden a sistemas de aprendizaje en linea y presenciales-tradicionales en educacion secundaria y terciaria; los algoritmos mas utilizados el J48, Random Forest, SVM, Naive Bayes (cl a sificacion), y la regresion logistica y lineal (regresion); los datos de evaluacion y los obtenidos de la interaccion del estudiante con el entorno de aprendizaje son las variables mas relevantes; finalmente, la anticipacion en la prediccion varia segun el tipo de sistema educativo. Palabras clave: Data Mining Educativo; Analitica de Aprendizaje; prediccion temprana del rendimiento academico; sistemas de deteccion temprana; estudiantes en riesgo de abandono.

• Publisher: Colegio Oficial De Psicologos Del Principado De Asturias,Colegio Oficial de Psicólogos (PSICODOC)
• Subject: Data mining / Distance learning / Literature reviews / Systematic review