Prediction of Student Dropout in E-Learning Program Through the Use of Machine Learning Method

Mingjie Tan,Peiji Shao

doi:10.3991/ijet.v10i1.4189

Abstract

The high rate of dropout is a serious problem in E-learning program. Thus it has received extensive concern from the education administrators and researchers. Predicting the potential dropout students is a workable solution to prevent dropout. Based on the analysis of related literature, this study selected student’s personal characteristic and academic performance as input attributions. Prediction models were developed using Artificial Neural Network (ANN), Decision Tree (DT) and Bayesian Networks (BNs). A large sample of 62375 students was utilized in the procedures of model training and testing. The results of each model were presented in confusion matrix, and analyzed by calculating the rates of accuracy, precision, recall, and F-measure. The results suggested all of the three machine learning methods were effective in student dropout prediction, and DT presented a better performance. Finally, some suggestions were made for considerable future research.

Highlights

The scale of E-learning has expanded continuously in the past 10 years due to its unique characteristic of being unconstrained by time or geographical limits
Nichols et al made use of ordinal regression for analyzing the data obtained from 187questionnaires returned by distance education students; the results showed that among four sets of attributions, only previous academic performance exhibited a strong correlation with dropout [21]
The research can be divided into the following four steps: Step 1, Extract attribution data related to student dropouts from the information systems of online educational institutions, construct the training data set and feed the data into the dropout prediction model

Summary

Introduction

The scale of E-learning has expanded continuously in the past 10 years due to its unique characteristic of being unconstrained by time or geographical limits. The number of registered students in American colleges and universities who participated in at least one online course from 2002 to 2010 has maintained an annual growth rate of about 10-20%, and in 2010 the number reached 6.14 million, accounting for 31.3% of all registered students [1]. According to statistics from the Chinese Ministry of Education, in 2011, the scale of distance education for bachelor/college students reached 4.53 million persons [2]. Along with the rapid growth of E-learning, its problem of having a much higher student dropout rate than traditional learning has become more prominent. In China, the dropout rate for traditional learning is about 5%, while the dropout rate for E-learning is as high as 15-40% [5,6,7]

Objectives

Methods

Conclusion