Predicting Students’ Academic Procrastination in Blended Learning Course Using Homework Submission Data

Aftab Akram,Ronghua Lin,Yong Tang,Chengzhou Fu,Muhammad Yaqoob Javed,Yuncheng Jiang,Yuyao Li

doi:10.1109/access.2019.2930867

Abstract

Academic procrastination has been reported affecting students' performance in computer-supported learning environments. Studies have shown that students who demonstrate higher procrastination tendencies achieve less than the students with lower procrastination tendencies. It is important for a teacher to be aware of the students' behaviors especially their procrastination trends. EDM techniques can be used to analyze data collected through computer-supported learning environments and to predict students' behaviors. In this paper, we present an algorithm called students' academic performance enhancement through homework late/non-submission detection (SAPE) for predicting students' academic performance. This algorithm is designed to predict students with learning difficulties through their homework submission behaviors. First, students are labeled as procrastinators or non-procrastinators using k-means clustering algorithm. Then, different classification methods are used to classify students using homework submission feature vectors. We use ten classification methods, i.e., ZeroR, OneR, ID3, J48, random forest, decision stump, JRip, PART, NBTree, and Prism. A detailed analysis is presented regarding performance of different classification methods for different number of classes. The analysis reveals that in general the prediction accuracy of all methods decreases with increase in the number of classes. However, different methods perform best or worst for different number of classes.

Highlights

On-line learning management system (LMS) provides a flexible and efficient way to promote beyond classroom interactions between students and teachers
The on-line LMSs rise pedagogical challenges for teachers, since many students fail to adapt to the requirements of on-line learning environments
The algorithm 2 details the steps taken to verify the correctness of feature vector

Summary

Introduction

On-line learning management system (LMS) provides a flexible and efficient way to promote beyond classroom interactions between students and teachers. Such systems can store abundant data regarding students’ and teachers’ interactions with the system. The on-line LMSs rise pedagogical challenges for teachers, since many students fail to adapt to the requirements of on-line learning environments. Many studies have reported that students face challenges while they are learning through on-line. References [4] and [5] reported that procrastination is frequently observed behavior in on-line learning environments. References [6] and [7] have reported the negative effect of procrastination on students’ achievement. By applying state-of-the-art data mining and machine learning techniques on students’ behavioral data acquired from LMS logs, algorithms can be built which can be used to predict students’ future behaviors [8]

Objectives

Results

Discussion

Conclusion