Machine learning techniques have become increasingly important in education for predicting student academic performance and providing timely interventions. This paper explores the application of machine learning to predict the performance of undergraduate EFL students in Algeria, aiming to enhance academic outcomes. It proposes a novel hybrid approach that integrates Support Vector Machine (SVM) with Dragonfly Algorithm (DA) to optimize prediction accuracy. Different influencing dataset parameters, including demographic data, learning behaviors, psychological factors, and assessment records of the students, were selected as input variables, while student performance was chosen as the output. R², MAE, and RMSE metrics were used to measure the accuracy of the developed model. The results show that the DA-SVM model significantly outperforms conventional machine learning techniques, establishing it as a promising tool for educational institutions to identify at-risk students and implement targeted interventions. This study contributes to the discourse on integrating technology in education by demonstrating the transformative potential of machine learning in optimizing student outcomes in Algerian universities and beyond, and promoting data-driven approaches to educational excellence.

Authors:
Asma Melouah, University of Medea, Algeria
Maamar Laidi, University of Medea, Algeria
Achwak Madani, University of Medea, Algeria

About the Presenter(s)
Dr. Asma Melouah is currently an associate professor in the Faculty of Letters and Languages at the University of Medea, Algeria.

Connect on Linkedin
https://www.linkedin.com/in/asma-melouah/

Connect on ResearchGate
https://www.researchgate.net/profile/Asma-Melouah?ev=hdr_xprf

See this presentation on the full schedule – Saturday Schedule

Bookmark