Scholarlink

<p>Learning analytics has considerable potential to support individualized classroom instruction by using artificial intelligence (AI) to analyze data generated through students’ interactions with digital technologies. While learning analytics has traditionally focused on specific digital technologies such as intelligent tutoring systems or MOOCs, its application to regular classroom instruction remains limited. However, effective classroom learning analytics requires integrating data from multiple digital technologies and interpreting them through domain-specific models of competence development (learning progressions). Such models connect learning processes to long-term competence development, enabling teachers to monitor students’ trajectories and adapt instruction to individual needs. The present focused collection of articles introduces a series of studies demonstrating how AI-driven learning analytics can be implemented in authentic classroom settings across mathematics, chemistry, and higher education. These studies show that AI can help reconstruct students’ learning trajectories, identify learners at risk, and provide timely evidence for instructional decision-making. Taken together the articles demonstrate that combining AI, digital technologies, and theory-based competence models can transform learning analytics from technology-specific applications into a powerful tool for individualized teaching and educational research.</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

Learning analytics: Artificial intelligence and learning in classroom instruction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月14日

查看全文
  • Knut Neumann

摘要

Learning analytics has considerable potential to support individualized classroom instruction by using artificial intelligence (AI) to analyze data generated through students’ interactions with digital technologies. While learning analytics has traditionally focused on specific digital technologies such as intelligent tutoring systems or MOOCs, its application to regular classroom instruction remains limited. However, effective classroom learning analytics requires integrating data from multiple digital technologies and interpreting them through domain-specific models of competence development (learning progressions). Such models connect learning processes to long-term competence development, enabling teachers to monitor students’ trajectories and adapt instruction to individual needs. The present focused collection of articles introduces a series of studies demonstrating how AI-driven learning analytics can be implemented in authentic classroom settings across mathematics, chemistry, and higher education. These studies show that AI can help reconstruct students’ learning trajectories, identify learners at risk, and provide timely evidence for instructional decision-making. Taken together the articles demonstrate that combining AI, digital technologies, and theory-based competence models can transform learning analytics from technology-specific applications into a powerful tool for individualized teaching and educational research.