Scholarlink

<p>Intelligent education, in the modern context, offers huge opportunities for the transformative integration of AI and IoT in enhancing language learning. This study proposes an English learning recommendation system that applies AI and IoT technologies to realize adaptive, context-sensitive, and learner-centered educational experiences. The dataset used for the system’s development is simulated AI-IoT English learning data from Kaggle, rather than real-world learner data. IoT-enabled devices comprising smart wearables, mobile sensors, and ambient learning environments gather real-time data from learners’ locations, engagement level, usage patterns of devices, and environmental condition 1,000 simulated learner interaction records. Integrating these IoT-driven behavioral signals with academic performance metrics, the system generates and dynamically adjusts personalized learning paths according to the language proficiency of every learner, their needs for improving vocabulary, and study habits. To handle data sparsity and limited recommendation diversity challenges, this work uses a DCR-PAtt-RNN model. The model synthesizes robust learner profiles, which improves the variety and relevance of the recommended content. Experimental results demonstrate that the proposed Python-based system attains high accuracy at 98.5%. Besides, it outperforms learning efficiency through increased retention rates and enhanced user satisfaction compared to the traditional static delivery systems. Overall, the proposed system reflects the potential of AI-IoT convergence in building intelligent, personalized learning ecosystems that support autonomous, immersive, and effective English language acquisition.</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

Design of a personalized English learning recommendation system based on AI and IoT

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月11日

查看全文
  • Jiangli Tian,
  • Zhihui Liu

摘要

Intelligent education, in the modern context, offers huge opportunities for the transformative integration of AI and IoT in enhancing language learning. This study proposes an English learning recommendation system that applies AI and IoT technologies to realize adaptive, context-sensitive, and learner-centered educational experiences. The dataset used for the system’s development is simulated AI-IoT English learning data from Kaggle, rather than real-world learner data. IoT-enabled devices comprising smart wearables, mobile sensors, and ambient learning environments gather real-time data from learners’ locations, engagement level, usage patterns of devices, and environmental condition 1,000 simulated learner interaction records. Integrating these IoT-driven behavioral signals with academic performance metrics, the system generates and dynamically adjusts personalized learning paths according to the language proficiency of every learner, their needs for improving vocabulary, and study habits. To handle data sparsity and limited recommendation diversity challenges, this work uses a DCR-PAtt-RNN model. The model synthesizes robust learner profiles, which improves the variety and relevance of the recommended content. Experimental results demonstrate that the proposed Python-based system attains high accuracy at 98.5%. Besides, it outperforms learning efficiency through increased retention rates and enhanced user satisfaction compared to the traditional static delivery systems. Overall, the proposed system reflects the potential of AI-IoT convergence in building intelligent, personalized learning ecosystems that support autonomous, immersive, and effective English language acquisition.