Scholarlink

The objective of this work is to develop an improved machine learning (ML) model to predict low-engagement students in virtual learning environments (VLEs). This model will address classification performance issues on imbalanced class data in a dataset of VLE students. To enhance the classification capabilities of the used data mining methods, this study employs the synthetic minority oversampling technique (SMOTE) approach. The study utilizes many predictive models, including logistic regression, decision tree, K-nearest neighbor, Naïve Bayes classifier, support vector machines, and XGBoost. In this work, we looked at the effects of data resampling by employing the SMOTE data balancing technique. When classifying class data from an unbalanced dataset, the ML classification algorithms are expected to perform more accurately, precisely, and sensitively when the class balancing techniques are applied.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predicting Student Engagement in Virtual Learning Environments Using ML Approaches with Data Balancing Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Lediana Shala Riza,
  • Lejla Abazi Bexheti

摘要

The objective of this work is to develop an improved machine learning (ML) model to predict low-engagement students in virtual learning environments (VLEs). This model will address classification performance issues on imbalanced class data in a dataset of VLE students. To enhance the classification capabilities of the used data mining methods, this study employs the synthetic minority oversampling technique (SMOTE) approach. The study utilizes many predictive models, including logistic regression, decision tree, K-nearest neighbor, Naïve Bayes classifier, support vector machines, and XGBoost. In this work, we looked at the effects of data resampling by employing the SMOTE data balancing technique. When classifying class data from an unbalanced dataset, the ML classification algorithms are expected to perform more accurately, precisely, and sensitively when the class balancing techniques are applied.