International Journal of Modern Education and Computer Science (IJMECS)
IJMECS Vol. 16, No. 4, 8 Aug. 2024
Cover page and Table of Contents: PDF (size: 864KB)
Students’ Results Prediction Using Machine Learning Algorithms and Online Learning during the COVID-19 Pandemic
PDF (864KB), PP.17-34
Views: 0 Downloads: 0
Author(s)
Index Terms
Machine Learning, Prediction, Classifiers, Random Forest, J48, MLP, NB, Online learning, Academic performance
Abstract
Machine learning-based prediction models are valuable prediction tools for assessing university performance as well as decision support tools for university governance and higher education system design. The prediction of student outcomes to enhance learning and teaching quality is one subject that has attracted considerable attention for different purposes. The first objective of this study is to develop and validate a prediction model using Machine Learning algorithms that predict students' outcomes in the case of Moroccan universities based only on the outcomes of courses taken in the previous semesters of university studies. This prediction model can be used as a basis for many subsequent studies on different aspects of higher education such as governance, pedagogy, etc. As a first application, we explore the responses of this prediction tool to analyze the outputs of the online learning experience that took place during the Covid-19 pandemic period. To achieve this, four machine learning algorithms are tested such as J48 decision tree, Random Forest, Multilayer Perceptron, and Naïve Bayes. The experimentations are developed by using Weka and the two metrics “accuracy” and “ROC Area” enable to assess the predictive performance of the models. The obtained results show that the Random Forest-based model provides superior results, as evidenced by its accuracy-ROC area, which reached an accuracy of 90% with a ROC Area of 95%. The use of this model to explore the outcomes of the distance learning experience taken during the Covid-19 pandemic, reveals a failure in the prediction performance of the model during the Covid-19 pandemic period, which indicates a change in the system's behavior during this period when teaching moved to the full online version in the year 2019/2020 and returned fully face-to-face in the 2021/2022 year. The failure in the machine learning algorithms' performance when the system changes its behavior can be a limitation of using prediction models based on machine learning in this context. On the other hand, these models can be used if they are properly designed to identify changes in the behavior of a system as shown in this study. Therefore, the proposed Random Forest-based model has the capability to forecast student outcomes accurately and can be applied for diverse analyses within the Moroccan education system. These analyses include but are not limited to identifying students at risks, guiding student orientation, assessing the influence of teaching approaches on student achievement, and evaluating training effectiveness, among others.
Cite This Paper
Najat Messaoudi, Jaafar K. Naciri, Bahloul Bensassi, "Students' Results Prediction Using Machine Learning Algorithms and Online Learning during the COVID-19 Pandemic", International Journal of Modern Education and Computer Science(IJMECS), Vol.16, No.4, pp. 17-34, 2024. DOI:10.5815/ijmecs.2024.04.02
Reference
[1]X. Zhang et W. Shi, «Research about the university teaching performance evaluation under the data envelopment method,» Cognitive Systems Research, vol. 56, pp. 108-115, 2019.
[2]S. You, K. Zheng Zhou et L. Jia, «How does human capital foster product innovation? The contingent roles of industry cluster features,» Journal of Business Research, vol. 130, pp. 335-347, 2021.
[3]K. Janzen, R. Panitz et J. Glückler, «Education premium and the compound impact of universities on their regional economy,» Research Policy, vol. 51, 2022.
[4]A. Carrascal Incera, A. Kitsos et D. G. Posada, «Universities, students and regional economies: a symbioticrelationship?,» Regional studies, vol. 56, n° %16, pp. 892-908, 2022.
[5]R. Yang, «Globalisation and Higher Education Development: A Critical Analysis,» International Review of Education , vol. 49, pp. 269-291, 2003.
[6]J. Youtiea et P. Shapira, «Building an innovation hub: A case study of the transformation of university roles in regional technological and economic development,» Research Policy, vol. 37, pp. 1188-1204, 2008.
[7]H.-Y. Wu, J.-K. Chen, I.-S. Chen et H.-H. Zhuo, «Ranking universities based on performance evaluation by a hybrid MCDM,» Measurement, vol. 45, pp. 856-880, 2012.
[8]T. Kattoua, M. Al-Lozi et A. Alrowwad, «A Review of Literature on E-Learning Systems in Higher Education,» International Journal of Business Management and Economic Research, vol. 7, n° %15, pp. 754-762, 2016.
[9]V. Milicevic, N. Denic, Z. Milicevic , L. Arsic, M. Spasic-Stojkovic, D. Petkovic, J. Stojanovic, M. Krkic, N. S. Milovancevic et A. Jovanovic, «E-learning perspectives in higher education institutions,» Technological Forecasting & Social Change, vol. 166, 2021.
[10]E. Djeki, J. Dégila, C. Bondiombouy et M. H. Alhassan, «E learning bibliometric analysis from 2015 to 2020,» Journal of Computers in Education, vol. 9, n° %14, pp. 727-754, 2022.
[11]X. Chen, D. Zou, H. Xie et F. Lee Wang, «Past, present, and future of smart learning: a topic based bibliometric analysis,» International Journal of Educational Technology in Higher Education, vol. 18, n° %12, 2021.
[12]S. K. S. Cheung, L. F. Kwok et H. H. Yang , «Shaping the future learning environments with smart elements: challenges and opportunities,» International Journal of Educational Technology in Higher Education, vol. 18, n° %116, 2021.
[13]S. H. Hashemi Petrudi, H. Ghomi et M. Mazaheriasad, «An Integrated Fuzzy Delphi and Best Worst Method (BWM) for performance measurement in higher education,» Decision Analytics Journal, vol. 4, 2022.
[14]J. Wang, «SOA-based Information Integration Platform for Educational Management Decision Support System,» Mathematical Problems in Engineering, 2022.
[15]N. Messaoudi, J. Khalid Naciri et B. Bensassi, «Mathematical modelling of output responses and performance variations of an education system due to changes in input parameters,» Advances in Science, Technology and Engineering Systems, vol. 6, n° %11, pp. 327-335, 2021.
[16]M. Tin, A. Panwar et M. Pant, «DEA for Measuring the Performance of Higher Education Sector: A Case Study of Myanmar,» chez Proceedings of the Seventh International Conference on Mathematics and Computing, 2022.
[17]O. I. Ramzi, A. V. Subbarayalu, N. K. Al-Kahtani, A. Al Kuwaiti, T. M. Alanzi, A. Alaskar, S. Prabaharan, V. Raman, M. S. M. Gibreel et N. S. Alameri, «Factors influencing service quality performance of a Saudi higher education institution: Public health program students' perspectives,» Informatics in Medicine Unlocked, vol. 28, 2022.
[18]L. L. Klein, K. M. Vieira, D. R. Marçal et J. R. Lima Pereira, «Lean management practices perception and their influence on organizational performance in a public Higher Education Institution,» TQM Mag., Vols. %1 sur %2ahead-of-print No. ahead-of-print, 2022.
[19]UNESCO, «Education, Policy & Strategy : Simulation Model EPSSim Version 2.1,» 2005.
[20]G. Akçapınar, A. Altun et P. Aşkar, «Using learning analytics to develop early-warning system for at-risk students,» International Journal of Educational Technology in Higher Education, vol. 16, 2019.
[21]Y. Nieto, V. Gacía-Díaz, C. Montenegro, C. Camilo González et R. González Crespo, «Usage of Machine Learning for Strategic Decision Making at Higher Educational Institutions,» IEEE Access, 2019.
[22]E. Alyahyan et D. Düştegör, «Predicting academic success in higher education: literature review and best practices,» International Journal of Educational Technology in Higher Education, pp. 1-21, 2020.
[23]A. Gonzalez-Nucamendi, J. Noguez, L. Neri, V. Robledo-Rella, R. M. G. Garcia-Castelan et D. Escobar-Castillejos, «The prediction of academic performance using engineering student's profiles,» Computers and Electrical Engineering, vol. 93, 2021.
[24]H. Zeineddine, U. Braendle et A. Farah, «Enhancing prediction of student success: Automated machine learning approach,» Computers and Electrical Engineering, vol. 89, 2021.
[25]N. O. Abdulwahid, S. Fakhfakh et I. Amous, «Simulating and Predicting Students’ Academic Performance Using a New Approach based on STEAM Education,» Journal of Universal Computer Science, vol. 28, n° %112, pp. 1252-1281, 2022.
[26]A. Namoun et A. Alshanqiti, «Predicting Student Performance Using Data Mining and Learning Analytics Techniques: A Systematic Literature Review,» Applied Sciences, vol. 11, n° %1237, 2021.
[27]L. Mansangu, A. Jadhav et R. Ajoodha, «Predicting Student Academic Performance Using Data Mining Techniques,» Advances in Science, Technology and Engineering Systems Journal, vol. 6, n° %11, pp. 153-163, 2021.
[28]N. Priyasadie et S. Mohammad Isa, «Educational Data Mining in Predicting Student Final Grades on Standardised Indonisia Data Pokok Pendidikan Data Set,» International Journal of Advanced Computer Science and Applications, vol. 12, n° %112, 2021.
[29]S. Fida, N. Masood, N. Tariq et F. Qayyum, «A Novel Hybrid Ensemble Clustering Technique for Student Performance Prediction,» Journal of Universal Computer Science,, vol. 28, n° %18, pp. 777-798, 2022.
[30]A. Roy, M. R. Rahman, M. Nazrul Islam, M. Nafiz Imtiaz Saimon, M. A. Alfaz et A.-A.-S. Jaber, «A Deep Learning Approach to Predict Academic Result and Recommend Study Plan for Improving Student's Academic Performance,» chez International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS 2021), Erode, India, 2021.
[31]R. R. Bouckaert, E. Frank, M. Hall, R. Kirkby, P. Reutemann, A. Seewald et D. Scuse, WEKA Manual for Version 3-7-8, Hamilton: University of Waikato, 2013.
[32]G. Matafeni et R. Ajoodha, «Using Big Data Analytics to Predict Learner Attrition based on First Year Marks at a South African University,» Advances in Science, Technology and Engineering Systems Journal, vol. 5, pp. 920-926, 2020.
[33]Sana, I. F. Siddiqui et Q. A. Arain, «Analyzing students' academic performance through educational data mining,» 3C Tecnologia. Glosas de innovacion aplicadas a la pyme, pp. 402-421, 2019.
[34]A. Fazal, I. Fakhund, A. Rahmani, R. Azhar et A. Masood Khattak, «A Predictive Model for Predicting Students Academic Performance,» chez 10th International Conference on Information, Intelligence, Systems and Applications (IISA), 2019.
[35]A. Siddique, A. Jan, F. Majeed, A. I. Qahmash, N. N. Quadri et M. O. Abdul Wahab, «Predicting Academic Performance Using an Efficient Model Based on Fusion of Classifiers,» Applied Sciences, vol. 11, pp. 1-19, 2021.
[36]W. S. Bhaya, «Review of Data Preprocessing Techniques in Data Mining,» Journal of Engineering and Applied Sciences, vol. 12, n° %116, pp. 4102-4107, 2017.
[37]A.-S. Hoffait et M. Schyns, «Early detection of university students with potential difficulties,» Decision Support Systems, vol. 101, pp. 1-11, 2017.
[38]A. M. Shahiri, W. Husain et N. Abdul Rashid, «A Review on Predicting Student's Performance Using Data Mining Techniques,» Procedia Computer Science, vol. 72, pp. 414-422, 2015.
[39]V. L. Miguéis, A. Freitas, P. J. Garcia et A. Silva, «Early segmentation of students according to their academic performance: A predictive modelling approach,» Decision Support Systems, vol. 115, pp. 36-51, 2018.
[40]M. A. Jassim, «Analysis of the Performance of the Main Algorithms for Educational Data Mining: A Review,» chez IOP Conference Series: Materials Science and Engineering, 2021.
[41]M. b. Hossin et M. N. Sulaiman, «A review on Evaluation Metrics for Data Classification Evaluations,» International Journal of Data Mining & Knowledge Management Process, vol. 5, n° %12, 2015.
[42]T. Fawcett, «An introduction to ROC analysis,» Pattern Recognition Letters, vol. 27, n° %18, pp. 861-874, 2006.
[43]A. S. Hashim, W. A. Awadh et A. K. Hamoud, «Student Performance Prediction Model based on Supervised Machine Learning Algorithms,» chez IOP Conference Series: Materials Science and Engineering, 2020.
[44]M. N. Yakubu et A. M. Abubakar, «Applying machine learning approach to predict students’ performance in higher educational institutions,» Kybernetes, vol. 51, n° %12, pp. 916-934, 2022.
[45]S. Iglesias-Pradas, Á. Hernández-García, J. C.-P. Chaparro-Peláez et J. L. Prieto, «Emergency remote teaching and students’ academic performance in higher education during the COVID-19 pandemic: A case study,» Computers in Human Behavior, vol. 119, 2021.
[46]G. K. Saw, C.-N. Chang, U. Lomelí et M. Zhi, «Fall Enrollment and Delayed Graduation Among STEM Students during the COVID-19 Pandemic,» Network for Research and Evaluation in Education (NREED) Data brief, pp. 1-5, 2020.
[47]M. García-Alberti, F. Suárez, I. Chiyón et J. C. Mosquera Feijoo, «Challenges and Experiences of Online Evaluation in Courses of Civil Engineering during the Lockdown Learning Due to the Covid-19 Pandemic,» Education Science, vol. 11, n° %159, 2021.