Scholarlink

The integration of generative AI (genAI) chatbots into Massive Open Online Courses (MOOCs) presents new opportunities for supporting self-regulated learning (SRL). This study examines 1,302 chatbot interactions from two Austrian blended MOOCs, where a retrieval-augmented generation (RAG) chatbot based on GPT 4o-mini was deployed to assist students. Using the process-action framework by Lai (2024), we categorize chatbot interactions into key SRL processes: defining, seeking, engaging, and reflecting. Results show that students predominantly use the chatbot for information retrieval, content summarization, and quiz-based reinforcement, with 41% of interactions classified as information search queries and 17% as rehearsal. However, engagement with metacognitive SRL strategies, such as goal setting and self-evaluation, remains low. Additionally, non-learning interactions, including humor-driven conversations, functional queries, and prompt injection attempts, showcase ways students interact with AI in educational settings. Based on our findings, we propose refinements to the existing SRL process-action framework, incorporating new categories to better account for genAI chatbot-specific interactions, such as Evaluation of Information Quality and Reformatting. We discuss implications for chatbot integration in MOOCs, emphasizing AI-generated quizzes, structured feedback, and safeguards against misuse.

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

Exploring GenAI Chatbots in MOOCs: Analyzing Student Interactions and Self-regulated Learning Behaviors

  • 会议论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年

查看全文
  • Benedikt Brünner,
  • Martin Ebner,
  • Sandra Schön

摘要

The integration of generative AI (genAI) chatbots into Massive Open Online Courses (MOOCs) presents new opportunities for supporting self-regulated learning (SRL). This study examines 1,302 chatbot interactions from two Austrian blended MOOCs, where a retrieval-augmented generation (RAG) chatbot based on GPT 4o-mini was deployed to assist students. Using the process-action framework by Lai (2024), we categorize chatbot interactions into key SRL processes: defining, seeking, engaging, and reflecting. Results show that students predominantly use the chatbot for information retrieval, content summarization, and quiz-based reinforcement, with 41% of interactions classified as information search queries and 17% as rehearsal. However, engagement with metacognitive SRL strategies, such as goal setting and self-evaluation, remains low. Additionally, non-learning interactions, including humor-driven conversations, functional queries, and prompt injection attempts, showcase ways students interact with AI in educational settings. Based on our findings, we propose refinements to the existing SRL process-action framework, incorporating new categories to better account for genAI chatbot-specific interactions, such as Evaluation of Information Quality and Reformatting. We discuss implications for chatbot integration in MOOCs, emphasizing AI-generated quizzes, structured feedback, and safeguards against misuse.