Scholarlink

<p>With the rapid development of online education worldwide, how to assess its teaching quality has become an important research topic. This study aims to develop a deep learning-based quality assessment model for online legal education to comprehensively assess students’ learning behaviors, interactive communication and learning outcomes. By analyzing students’ learning behavior data and online discussion text data, this study establishes a set of quality assessment index system that includes multiple dimensions such as teaching resources, learning support services, interactive communication mechanism and student satisfaction. Adopting deep learning technology, this study designs a multimodal deep learning architecture that is capable of processing different types of data inputs and fusing them into a comprehensive quality assessment score. The experimental results show that the model proposed in this paper outperforms other models in terms of accuracy, F1 score, precision and recall in predicting student performance, demonstrating its advantages in handling related tasks.</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

Online education quality assessment model based on deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月17日

查看全文
  • Xueliang Mao

摘要

With the rapid development of online education worldwide, how to assess its teaching quality has become an important research topic. This study aims to develop a deep learning-based quality assessment model for online legal education to comprehensively assess students’ learning behaviors, interactive communication and learning outcomes. By analyzing students’ learning behavior data and online discussion text data, this study establishes a set of quality assessment index system that includes multiple dimensions such as teaching resources, learning support services, interactive communication mechanism and student satisfaction. Adopting deep learning technology, this study designs a multimodal deep learning architecture that is capable of processing different types of data inputs and fusing them into a comprehensive quality assessment score. The experimental results show that the model proposed in this paper outperforms other models in terms of accuracy, F1 score, precision and recall in predicting student performance, demonstrating its advantages in handling related tasks.