Scholarlink

<p>Personalized course recommendations represent a significant problem in extensive e-learning platforms, as student preferences are in constant flux and educational environments are increasingly influenced by IoT-enabled interactions. Traditional recommendation algorithms generally regard user behavior as static or minimally contextualized, hence constraining their efficacy in dynamic and diverse learning settings. This research presents a context-sensitive sequential recommendation framework that concurrently models uncertainty, temporal learning patterns, and real-time contextual awareness. The proposed approach utilizes Conditional Variational Autoencoders to develop resilient latent representations of learners and courses amidst sparse and noisy interaction data, while a Transformer-based sequential model captures long-term dependencies in learning trajectories. In contrast to current methodologies, contextual signals obtained from IoT-enabled learning environments are explicitly integrated and amalgamated into the sequential decision-making process, enabling suggestions to adjust to situational learning settings rather than depending exclusively on prior encounters. The model is trained with a cohesive objective that harmonizes representation consistency and ranking accuracy, facilitating stable personalization across various learner profiles. Experimental assessments on various real-world MOOC datasets reveal consistent and statistically significant improvements over competitive baselines in both ranking and error metrics, validating the efficacy of incorporating uncertainty-aware modeling with context-driven sequential learning. The suggested method reinterprets course recommendation as a dynamic, context-sensitive process and establishes a scalable framework for intelligent e-learning systems designed to facilitate personalized learning trajectories within IoT-integrated digital education environments.</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

Context-aware sequential course recommendation via conditional variational autoencoders and transformer architectures in IoT-enabled E-learning systems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月1日

查看全文
  • Guanyu Chen,
  • Guangxin Han,
  • Shuhua Liu

摘要

Personalized course recommendations represent a significant problem in extensive e-learning platforms, as student preferences are in constant flux and educational environments are increasingly influenced by IoT-enabled interactions. Traditional recommendation algorithms generally regard user behavior as static or minimally contextualized, hence constraining their efficacy in dynamic and diverse learning settings. This research presents a context-sensitive sequential recommendation framework that concurrently models uncertainty, temporal learning patterns, and real-time contextual awareness. The proposed approach utilizes Conditional Variational Autoencoders to develop resilient latent representations of learners and courses amidst sparse and noisy interaction data, while a Transformer-based sequential model captures long-term dependencies in learning trajectories. In contrast to current methodologies, contextual signals obtained from IoT-enabled learning environments are explicitly integrated and amalgamated into the sequential decision-making process, enabling suggestions to adjust to situational learning settings rather than depending exclusively on prior encounters. The model is trained with a cohesive objective that harmonizes representation consistency and ranking accuracy, facilitating stable personalization across various learner profiles. Experimental assessments on various real-world MOOC datasets reveal consistent and statistically significant improvements over competitive baselines in both ranking and error metrics, validating the efficacy of incorporating uncertainty-aware modeling with context-driven sequential learning. The suggested method reinterprets course recommendation as a dynamic, context-sensitive process and establishes a scalable framework for intelligent e-learning systems designed to facilitate personalized learning trajectories within IoT-integrated digital education environments.