Scholarlink

This poster paper explores the extent to which Large Language Models (LLMs) could help teachers of online courses to design feedback interventions based on their learning designs. Using real course learning designs as input, together with predefined catalogs of potential problems, indicators, and feedback reactions grounded in feedback theories, our research showcases how ChatGPT-o1 is capable of suggesting feedback design decisions that are meaningful to human instructional designers. The results suggest that state-of-the-art LLMs, when asked to base their answers on a theory-driven design space, may assist novice teachers and instructional designers in incorporating pedagogically sound feedback interventions in their courses.

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

Assisting Teachers in the Design of Feedback for Online Learning Using Large Language Models: A Theory-Driven Approach

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Paraskevi Topali,
  • Alejandro Ortega-Arranz,
  • Miguel L. Bote-Lorenzo,
  • Juan I. Asensio-Pérez

摘要

This poster paper explores the extent to which Large Language Models (LLMs) could help teachers of online courses to design feedback interventions based on their learning designs. Using real course learning designs as input, together with predefined catalogs of potential problems, indicators, and feedback reactions grounded in feedback theories, our research showcases how ChatGPT-o1 is capable of suggesting feedback design decisions that are meaningful to human instructional designers. The results suggest that state-of-the-art LLMs, when asked to base their answers on a theory-driven design space, may assist novice teachers and instructional designers in incorporating pedagogically sound feedback interventions in their courses.