Scholarlink

Recommender systems (RS) in e-learning platforms, often operate as black boxes, undermining user trust and engagement. This paper introduces a novel Context-Aware Explainable Recommender System (CAExRS) designed to enhance transparency in e-learning (like Moodle). We propose a method that combines contextual information with explainable AI techniques to offer personalized recommendations with clear, human-readable justifications. Our approach not only improves the relevance of content suggestions but also fosters trust by providing students and instructors with understandable explanations. This work aims to improve student engagement and system transparency, paving the way for more effective, user-centric educational experiences.

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

Enhancing E-Learning with Context-Aware Explainable Recommender Systems

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Kaoutar Errakha,
  • Amina Samih,
  • Abderrahim Marzouk,
  • Ayoub Krari

摘要

Recommender systems (RS) in e-learning platforms, often operate as black boxes, undermining user trust and engagement. This paper introduces a novel Context-Aware Explainable Recommender System (CAExRS) designed to enhance transparency in e-learning (like Moodle). We propose a method that combines contextual information with explainable AI techniques to offer personalized recommendations with clear, human-readable justifications. Our approach not only improves the relevance of content suggestions but also fosters trust by providing students and instructors with understandable explanations. This work aims to improve student engagement and system transparency, paving the way for more effective, user-centric educational experiences.