Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh.
PLoS One. 2024 Sep 3;19(9):e0307536. doi: 10.1371/journal.pone.0307536. eCollection 2024.
Educational Data Mining (EDM) holds promise in uncovering insights from educational data to predict and enhance students' performance. This paper presents an advanced EDM system tailored for classifying and improving tertiary students' programming skills. Our approach emphasizes effective feature engineering, appropriate classification techniques, and the integration of Explainable Artificial Intelligence (XAI) to elucidate model decisions. Through rigorous experimentation, including an ablation study and evaluation of six machine learning algorithms, we introduce a novel ensemble method, Stacking-SRDA, which outperforms others in accuracy, precision, recall, f1-score, ROC curve, and McNemar test. Leveraging XAI tools, we provide insights into model interpretability. Additionally, we propose a system for identifying skill gaps in programming among weaker students, offering tailored recommendations for skill enhancement.
教育数据挖掘（EDM）有望从教育数据中挖掘洞察，以预测和提高学生的表现。本文提出了一个专门用于分类和提高大学生编程技能的高级 EDM 系统。我们的方法强调有效的特征工程、适当的分类技术以及可解释人工智能（XAI）的集成，以阐明模型决策。通过包括消融研究和对六种机器学习算法的评估在内的严格实验，我们引入了一种新颖的集成方法 Stacking-SRDA，该方法在准确性、精度、召回率、f1 分数、ROC 曲线和 McNemar 检验方面优于其他方法。利用 XAI 工具，我们深入了解模型的可解释性。此外，我们提出了一个系统，用于识别编程能力较弱的学生的技能差距，并提供有针对性的技能提升建议。
