A Deep Neural Network-Based Prediction Model for Students' Academic Performance

Ghaith Al-Tameem; James Xue; Suraj Ajit; Triantafyllos Kanakis; Israa Hadi; Thar Baker; Mohammed Al-Khafaji; Rawaa Al-Jumeil

doi:10.1109/DESE54285.2021.9719552

A Deep Neural Network-Based Prediction Model for Students' Academic Performance

Ghaith Al-Tameem
, James Xue
, Suraj Ajit
, Triantafyllos Kanakis
, Israa Hadi
, Thar Baker
, Mohammed Al-Khafaji
, Rawaa Al-Jumeil

University of Sharjah

University of Northampton
University of Babylon
University of Reading
Liverpool John Moores University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

9 Scopus citations

Abstract

Education providers are increasingly using artificial techniques for predicting students' performance based on their interactions in Virtual Learning Environments (VLE). In this paper, the Open University Learning Analytics Dataset (OULAD), which contains student demographic information, assessment scores, number of clicks in the virtual learning environment and final results, etc, has been used to predict student performance. Various techniques such as standardisation and normalisation have been employed in the pre-processing stage. Spearman's correlation coefficient is used to measure the correlation between the activity types and the students' final results to determine the importance of the activities. Deep learning has been utilised to predict students' performance based on their engagement in the VLE. The empirical results show that our model has the ability to accurately predict student academic performance.

Original language	English
Title of host publication	2021 14th International Conference on Developments in eSystems Engineering, DeSE 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	364-369
Number of pages	6
ISBN (Electronic)	9781665408882
DOIs	https://doi.org/10.1109/DESE54285.2021.9719552
State	Published - 2021
Event	14th International Conference on Developments in eSystems Engineering, DeSE 2021 - Sharjah, United Arab Emirates Duration: 7 Dec 2021 → 10 Dec 2021

Publication series

Name	Proceedings - International Conference on Developments in eSystems Engineering, DeSE
Volume	2021-December
ISSN (Print)	2161-1343

Conference

Conference	14th International Conference on Developments in eSystems Engineering, DeSE 2021
Country/Territory	United Arab Emirates
City	Sharjah
Period	7/12/21 → 10/12/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 4 Quality Education

Keywords

Deep learning
correlation coefficient
student engagement
student performance

Access to Document

10.1109/DESE54285.2021.9719552

Cite this

Al-Tameem, G., Xue, J., Ajit, S., Kanakis, T., Hadi, I., Baker, T., Al-Khafaji, M., & Al-Jumeil, R. (2021). A Deep Neural Network-Based Prediction Model for Students' Academic Performance. In 2021 14th International Conference on Developments in eSystems Engineering, DeSE 2021 (pp. 364-369). (Proceedings - International Conference on Developments in eSystems Engineering, DeSE; Vol. 2021-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DESE54285.2021.9719552

Al-Tameem, Ghaith ; Xue, James ; Ajit, Suraj et al. / A Deep Neural Network-Based Prediction Model for Students' Academic Performance. 2021 14th International Conference on Developments in eSystems Engineering, DeSE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 364-369 (Proceedings - International Conference on Developments in eSystems Engineering, DeSE).

@inproceedings{608c768510e24a0286e97d9e7ba1415d,

title = "A Deep Neural Network-Based Prediction Model for Students' Academic Performance",

abstract = "Education providers are increasingly using artificial techniques for predicting students' performance based on their interactions in Virtual Learning Environments (VLE). In this paper, the Open University Learning Analytics Dataset (OULAD), which contains student demographic information, assessment scores, number of clicks in the virtual learning environment and final results, etc, has been used to predict student performance. Various techniques such as standardisation and normalisation have been employed in the pre-processing stage. Spearman's correlation coefficient is used to measure the correlation between the activity types and the students' final results to determine the importance of the activities. Deep learning has been utilised to predict students' performance based on their engagement in the VLE. The empirical results show that our model has the ability to accurately predict student academic performance.",

keywords = "Deep learning, correlation coefficient, student engagement, student performance",

author = "Ghaith Al-Tameem and James Xue and Suraj Ajit and Triantafyllos Kanakis and Israa Hadi and Thar Baker and Mohammed Al-Khafaji and Rawaa Al-Jumeil",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 14th International Conference on Developments in eSystems Engineering, DeSE 2021 ; Conference date: 07-12-2021 Through 10-12-2021",

year = "2021",

doi = "10.1109/DESE54285.2021.9719552",

language = "English",

series = "Proceedings - International Conference on Developments in eSystems Engineering, DeSE",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "364--369",

booktitle = "2021 14th International Conference on Developments in eSystems Engineering, DeSE 2021",

address = "United States",

}

Al-Tameem, G, Xue, J, Ajit, S, Kanakis, T, Hadi, I, Baker, T, Al-Khafaji, M & Al-Jumeil, R 2021, A Deep Neural Network-Based Prediction Model for Students' Academic Performance. in 2021 14th International Conference on Developments in eSystems Engineering, DeSE 2021. Proceedings - International Conference on Developments in eSystems Engineering, DeSE, vol. 2021-December, Institute of Electrical and Electronics Engineers Inc., pp. 364-369, 14th International Conference on Developments in eSystems Engineering, DeSE 2021, Sharjah, United Arab Emirates, 7/12/21. https://doi.org/10.1109/DESE54285.2021.9719552

A Deep Neural Network-Based Prediction Model for Students' Academic Performance. / Al-Tameem, Ghaith; Xue, James; Ajit, Suraj et al.
2021 14th International Conference on Developments in eSystems Engineering, DeSE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 364-369 (Proceedings - International Conference on Developments in eSystems Engineering, DeSE; Vol. 2021-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Deep Neural Network-Based Prediction Model for Students' Academic Performance

AU - Al-Tameem, Ghaith

AU - Xue, James

AU - Ajit, Suraj

AU - Kanakis, Triantafyllos

AU - Hadi, Israa

AU - Baker, Thar

AU - Al-Khafaji, Mohammed

AU - Al-Jumeil, Rawaa

PY - 2021

Y1 - 2021

N2 - Education providers are increasingly using artificial techniques for predicting students' performance based on their interactions in Virtual Learning Environments (VLE). In this paper, the Open University Learning Analytics Dataset (OULAD), which contains student demographic information, assessment scores, number of clicks in the virtual learning environment and final results, etc, has been used to predict student performance. Various techniques such as standardisation and normalisation have been employed in the pre-processing stage. Spearman's correlation coefficient is used to measure the correlation between the activity types and the students' final results to determine the importance of the activities. Deep learning has been utilised to predict students' performance based on their engagement in the VLE. The empirical results show that our model has the ability to accurately predict student academic performance.

AB - Education providers are increasingly using artificial techniques for predicting students' performance based on their interactions in Virtual Learning Environments (VLE). In this paper, the Open University Learning Analytics Dataset (OULAD), which contains student demographic information, assessment scores, number of clicks in the virtual learning environment and final results, etc, has been used to predict student performance. Various techniques such as standardisation and normalisation have been employed in the pre-processing stage. Spearman's correlation coefficient is used to measure the correlation between the activity types and the students' final results to determine the importance of the activities. Deep learning has been utilised to predict students' performance based on their engagement in the VLE. The empirical results show that our model has the ability to accurately predict student academic performance.

KW - Deep learning

KW - correlation coefficient

KW - student engagement

KW - student performance

UR - https://www.scopus.com/pages/publications/85126749080

U2 - 10.1109/DESE54285.2021.9719552

DO - 10.1109/DESE54285.2021.9719552

M3 - Conference contribution

AN - SCOPUS:85126749080

T3 - Proceedings - International Conference on Developments in eSystems Engineering, DeSE

SP - 364

EP - 369

BT - 2021 14th International Conference on Developments in eSystems Engineering, DeSE 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th International Conference on Developments in eSystems Engineering, DeSE 2021

Y2 - 7 December 2021 through 10 December 2021

ER -

Al-Tameem G, Xue J, Ajit S, Kanakis T, Hadi I, Baker T et al. A Deep Neural Network-Based Prediction Model for Students' Academic Performance. In 2021 14th International Conference on Developments in eSystems Engineering, DeSE 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 364-369. (Proceedings - International Conference on Developments in eSystems Engineering, DeSE). doi: 10.1109/DESE54285.2021.9719552

A Deep Neural Network-Based Prediction Model for Students' Academic Performance

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this