Search results

1 – 2 of 2
Content available
Article
Publication date: 3 July 2017

Rahila Umer, Teo Susnjak, Anuradha Mathrani and Suriadi Suriadi

The purpose of this paper is to propose a process mining approach to help in making early predictions to improve students’ learning experience in massive open online…

Abstract

Purpose

The purpose of this paper is to propose a process mining approach to help in making early predictions to improve students’ learning experience in massive open online courses (MOOCs). It investigates the impact of various machine learning techniques in combination with process mining features to measure effectiveness of these techniques.

Design/methodology/approach

Student’s data (e.g. assessment grades, demographic information) and weekly interaction data based on event logs (e.g. video lecture interaction, solution submission time, time spent weekly) have guided this design. This study evaluates four machine learning classification techniques used in the literature (logistic regression (LR), Naïve Bayes (NB), random forest (RF) and K-nearest neighbor) to monitor weekly progression of students’ performance and to predict their overall performance outcome. Two data sets – one, with traditional features and second, with features obtained from process conformance testing – have been used.

Findings

The results show that techniques used in the study are able to make predictions on the performance of students. Overall accuracy (F1-score, area under curve) of machine learning techniques can be improved by integrating process mining features with standard features. Specifically, the use of LR and NB classifiers outperforms other techniques in a statistical significant way.

Practical implications

Although MOOCs provide a platform for learning in highly scalable and flexible manner, they are prone to early dropout and low completion rate. This study outlines a data-driven approach to improve students’ learning experience and decrease the dropout rate.

Social implications

Early predictions based on individual’s participation can help educators provide support to students who are struggling in the course.

Originality/value

This study outlines the innovative use of process mining techniques in education data mining to help educators gather data-driven insight on student performances in the enrolled courses.

Details

Journal of Research in Innovative Teaching & Learning, vol. 10 no. 2
Type: Research Article
ISSN: 2397-7604

Keywords

To view the access options for this content please click here
Article
Publication date: 16 August 2019

Gomathy Ramaswami, Teo Susnjak, Anuradha Mathrani, James Lim and Pablo Garcia

This paper aims to evaluate educational data mining methods to increase the predictive accuracy of student academic performance for a university course setting. Student…

Abstract

Purpose

This paper aims to evaluate educational data mining methods to increase the predictive accuracy of student academic performance for a university course setting. Student engagement data collected in real time and over self-paced activities assisted this investigation.

Design/methodology/approach

Classification data mining techniques have been adapted to predict students’ academic performance. Four algorithms, Naïve Bayes, Logistic Regression, k-Nearest Neighbour and Random Forest, were used to generate predictive models. Process mining features have also been integrated to determine their effectiveness in improving the accuracy of predictions.

Findings

The results show that when general features derived from student activities are combined with process mining features, there is some improvement in the accuracy of the predictions. Of the four algorithms, the study finds Random Forest to be more accurate than the other three algorithms in a statistically significant way. The validation of the best-known classifier model is then tested by predicting students’ final-year academic performance for the subsequent year.

Research limitations/implications

The present study was limited to datasets gathered over one semester and for one course. The outcomes would be more promising if the dataset comprised more courses. Moreover, the addition of demographic information could have provided further representations of students’ performance. Future work will address some of these limitations.

Originality/value

The model developed from this research can provide value to institutions in making process- and data-driven predictions on students’ academic performances.

Details

Information and Learning Sciences, vol. 120 no. 7/8
Type: Research Article
ISSN: 2398-5348

Keywords

1 – 2 of 2