Scholarlink

Student engagement is a pivotal factor in enhancing learning outcomes, motivation, and academic success. This paper investigates the use of deep learning models to predict and enhance student engagement using the DAiSEE and MathSpring datasets. Among the tested models (CNN, VGG16, LSTM-CNN, and Transformers), CNN (88% accuracy on MathSpring) and VGG16 (80% accuracy on DAiSEE) demonstrated the best performance. The deployment of the top model in a web-based system enables real-time engagement monitoring, providing educators with an adaptive teaching tool. These findings underscore AI’s potential in personalized education and academic improvement.

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

Identifying and Predicting Student Engagement and Motivation Using Deep Learning Techniques

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Siham Essahraui,
  • Firdaous El Outmani,
  • Ibrahim Ouahbi,
  • Khalid El Makkaoui,
  • Mouncef Filali Bouami

摘要

Student engagement is a pivotal factor in enhancing learning outcomes, motivation, and academic success. This paper investigates the use of deep learning models to predict and enhance student engagement using the DAiSEE and MathSpring datasets. Among the tested models (CNN, VGG16, LSTM-CNN, and Transformers), CNN (88% accuracy on MathSpring) and VGG16 (80% accuracy on DAiSEE) demonstrated the best performance. The deployment of the top model in a web-based system enables real-time engagement monitoring, providing educators with an adaptive teaching tool. These findings underscore AI’s potential in personalized education and academic improvement.