The Reel Deal: Designing and Evaluating LLM-Generated Short-Form Educational Videos
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909774826700800 |
|---|---|
| author | Stavrinou, Lazaros Constantinides, Argyris Belk, Marios Vassiliou, Vasos Liarokapis, Fotis Constantinides, Marios |
| author_facet | Stavrinou, Lazaros Constantinides, Argyris Belk, Marios Vassiliou, Vasos Liarokapis, Fotis Constantinides, Marios |
| contents | Short-form videos are gaining popularity in education due to their concise and accessible format that enables microlearning. Yet, most of these videos are manually created. Even for those automatically generated using artificial intelligence (AI), it is not well understood whether or how they affect learning outcomes, user experience, and trust. To address this gap, we developed ReelsEd, which is a web-based system that uses large language models (LLMs) to automatically generate structured short-form video (i.e., reels) from lecture long-form videos while preserving instructor-authored material. In a between-subject user study with 62 university students, we evaluated ReelsEd and demonstrated that it outperformed traditional long-form videos in engagement, quiz performance, and task efficiency without increasing cognitive load. Learners expressed high trust in our system and valued its clarity, usefulness, and ease of navigation. Our findings point to new design opportunities for integrating generative AI into educational tools that prioritize usability, learner agency, and pedagogical alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05962 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Reel Deal: Designing and Evaluating LLM-Generated Short-Form Educational Videos Stavrinou, Lazaros Constantinides, Argyris Belk, Marios Vassiliou, Vasos Liarokapis, Fotis Constantinides, Marios Human-Computer Interaction Short-form videos are gaining popularity in education due to their concise and accessible format that enables microlearning. Yet, most of these videos are manually created. Even for those automatically generated using artificial intelligence (AI), it is not well understood whether or how they affect learning outcomes, user experience, and trust. To address this gap, we developed ReelsEd, which is a web-based system that uses large language models (LLMs) to automatically generate structured short-form video (i.e., reels) from lecture long-form videos while preserving instructor-authored material. In a between-subject user study with 62 university students, we evaluated ReelsEd and demonstrated that it outperformed traditional long-form videos in engagement, quiz performance, and task efficiency without increasing cognitive load. Learners expressed high trust in our system and valued its clarity, usefulness, and ease of navigation. Our findings point to new design opportunities for integrating generative AI into educational tools that prioritize usability, learner agency, and pedagogical alignment. |
| title | The Reel Deal: Designing and Evaluating LLM-Generated Short-Form Educational Videos |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2509.05962 |