Evaluating the Impact of LLM-guided Reflection on Learning Outcomes with Interactive AI-Generated Educational Podcasts
Vishnu Menon, Andy Cherney, Elizabeth B. Cloude, Li Zhang, Tiffany D. Do
TL;DR
This study investigated how embedding LLM-guided reflection prompts in AI-generated educational podcasts affects learning and user experience, finding no significant improvement in learning but a decrease in perceived attractiveness.
Contribution
It introduces LLM-guided reflection prompts in educational podcasts and evaluates their impact on learning outcomes and user experience.
Findings
Learning outcomes were similar across conditions.
Reflection prompts reduced perceived attractiveness.
Further research needed on reflective interactivity design.
Abstract
This study examined whether embedding LLM-guided reflection prompts in an interactive AI-generated podcast improved learning and user experience compared to a version without prompts. Thirty-six undergraduates participated, and while learning outcomes were similar across conditions, reflection prompts reduced perceived attractiveness, highlighting a call for more research on reflective interactivity design.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.