Curio: Enhancing STEM Online Video Learning Experience Through Integrated, Just-in-Time Help-Seeking

Online video learning platforms have broadened access to learning but often struggle to offer personalized, context-sensitive support when learners encounter complex, tightly-knit concepts, particularly from the STEM fields. This paper presents Curio, a novel help-seeking system capable of being integrated into existing video learning environments. Utilizing a platform-agnostic approach, Curio leverages Tesseract OCR and GPT-4 to provide real-time, personalized video recommendations and concept explanations. When confronted with complex content, learners can “capture” any on-screen text-based elements to instantly receive targeted assistance and continue their educational journey without diverting their focus to external resources. A controlled user study, comprising both quantitative measurements and qualitative interviews, was conducted with twenty-two participants to assess Curio’s efficacy in enhancing help-seeking experiences. The study revealed that Curio reduced the friction and decreased mental workload involved in the help-seeking process while maintaining effectiveness. A post-hoc analysis further revealed a correlation between learners’ prior knowledge and their performance with Curio.