Scholarlink

<p>Massive open online courses (MOOCs) provide abundant learning resources but also overwhelm learners with their sheer volume, leading to challenges such as data sparsity and cold-start issues in conventional recommendation systems. To address these challenges, we propose EGRec, a novel course recommendation model that combines knowledge graphs and Heterogeneous Graph Attention Networks to improve recommendation precision, diversity, and relevance. By integrating multimodal data and explicitly leveraging dynamic subgraphs, EGRec captures intricate semantic relationships between courses and knowledge points, and dynamically adapts to learners’ evolving preferences. Extensive experiments on three real MOOCs datasets (ASSISTments 2009, ASSISTments 2015, and XueTangX) show that EGRec achieves up to 4%–5% improvements over state-of-the-art methods in HR@20, nDCG@20, and MRR. Our contributions include the design of a dynamic graph-enhanced model architecture, a novel multimodal fusion strategy, and substantial empirical gains in recommendation accuracy. These results highlight EGRec’s potential to enhance tailored learning experiences. </p>

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

EGRec: a MOOCs course recommendation model based on knowledge graphs

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月31日

查看全文
  • Yuefeng Cen,
  • Shuai Jiang,
  • Wenxuan Cai,
  • Gang Cen

摘要

Massive open online courses (MOOCs) provide abundant learning resources but also overwhelm learners with their sheer volume, leading to challenges such as data sparsity and cold-start issues in conventional recommendation systems. To address these challenges, we propose EGRec, a novel course recommendation model that combines knowledge graphs and Heterogeneous Graph Attention Networks to improve recommendation precision, diversity, and relevance. By integrating multimodal data and explicitly leveraging dynamic subgraphs, EGRec captures intricate semantic relationships between courses and knowledge points, and dynamically adapts to learners’ evolving preferences. Extensive experiments on three real MOOCs datasets (ASSISTments 2009, ASSISTments 2015, and XueTangX) show that EGRec achieves up to 4%–5% improvements over state-of-the-art methods in HR@20, nDCG@20, and MRR. Our contributions include the design of a dynamic graph-enhanced model architecture, a novel multimodal fusion strategy, and substantial empirical gains in recommendation accuracy. These results highlight EGRec’s potential to enhance tailored learning experiences.