Enhancing Learning Algorithms in Computer Science on YouTube: A Personalized Educational System, EduTube AI

Abstract

In the context of self-directed computer science education, our studies show that learners often struggle to find high quality algorithm content that matches their current level and supports a coherent progression. Despite the popularity of platforms like YouTube, many users report challenges such as overwhelming search results, inconsistent instructional quality, and a lack of personalized learning paths. To explore these issues, we conducted a series of learner focused studies examining how individuals search for and engage with algorithm-related content online, and what barriers they encounter along the way. Drawing on these insights, we developed EduTube AI, a tool that integrates the YouTube API with GPT-4 to provide personalized video recommendations for algorithm learning. The system uses the learner's knowledge level, suggests relevant videos, and offers brief follow up quiz to reinforce the material. A follow-up study was conducted to gather user feedback on the tool's perceived relevance, structure, and support for learning progression. While the results are exploratory, they suggest directions for how AI-based systems might be used to support more adaptive and learner-centered experiences in open educational environments.