Web usage mining for predicting final marks of students that use Moodle courses

Abstract

This paper shows how web usage mining can be applied in e-learning systems in order to predict the marks that university students will obtain in the final exam of a course. We have also developed a specific Moodle mining tool oriented for the use of not only experts in data mining but also of newcomers like instructors and courseware authors. The performance of different data mining techniques for classifying students are compared, starting with the student's usage data in several Cordoba University Moodle courses in engineering. Several wellknown classification methods have been used, such as statistical methods, decision trees, rule and fuzzy rule induction methods, and neural networks. We have carried out several experiments using all available and filtered data to try to obtain more accuracy. Discretization and rebalance pre-processing techniques have also been used on the original numerical data to test again if better classifier models can be obtained. Finally, we show examples of some of the models discovered and explain that a classifier model appropriate for an educational environment has to be both accurate and comprehensible in order for instructors and course administrators to be able to use it for decision making.

Modeling Students’ Academic Performance Based on Their Interactions with the Online Learning Environment

“…The IF clause contains a combination of conditions for the predicting attributes. The THEN clause contains the predicted value for the class (Cristobal Romero et al, 2013). Numerous methods, such as classification based on associations (Liu, Hsu, & Ma, 1998) and CN2 (Clark & Niblett, 1989), have been proposed in the literature.…”

“…McCuaig and Baldwin (2012) asserted that the source log data produced by conventional LMS could be mined to predict the students' success or failure without requiring the results of formal assessments. Márquez-Vera, Cano, Romero, and Ventura (2013) also conducted a study to predict which students might fail a course using students' online performances.…”

Application of Data Mining and Process Mining approaches for improving e-Learning Processes

“…The types of prediction methods are: classification (target variable is a category), regression (target and background variables are numbers), the density score (predicted value is the probability density function). Using these methods to predict student performance and to determine the pattern of student behavior is considered in [27] and [28].…”

Rendimiento académico e interacción sociocognitiva de estudiantes en un entorno virtual

“…Sael, Marzak y Behja (2013) hallaron los estudiantes que más tiempo tuvieron sus sesiones abiertas obtuvieron puntuaciones buenas, aunque los autores sostienen que el tiempo de las sesiones no parece reflejar las puntuaciones en forma directa. Romero et al (2013b), utilizando bases de datos de los cursos de Moodle en función de predecir las calificaciones que obtendrían, desarrollaron una herramienta específica integrada al sistema para facilitar la ejecución de algoritmos de datos para usuarios no expertos (como docentes) y usuarios expertos (investigadores especializados). Llegaron a la conclusión de que la precisión obtenida no es muy alta (del orden del 65%) dado que predecir las calificaciones finales de los alumnos a partir de los datos de uso del web representa una tarea difícil.…”