From Passive Watching to Active Learning: Empowering Proactive Participation in Digital Classrooms with AI Video Assistant

TL;DR

The paper tackles the challenge of passive online learning by introducing SAM, a context-aware AI mentor embedded in a video-watching platform that supports real-time, content-specific questioning and explanations. Built on GPT-4o, SAM leverages video transcripts, slides, and LaTeX-rendered formulas to deliver personalized guidance and exports a learning-record PDF. Through pilot and main studies (n=25 and n=80, respectively), SAM demonstrates high answer accuracy ($97.6\%$) and user satisfaction, with notable knowledge gains among younger learners and students with flexible schedules, though effects vary by demographic and topic familiarity. The work highlights SAM’s potential to transform online education by increasing interactivity and learner ownership, while outlining limitations such as topic scope, prior knowledge variance, and platform constraints, and proposing future extensions to broader subjects and platforms.

Abstract

In online education, innovative tools are crucial for enhancing learning outcomes. SAM (Study with AI Mentor) is an advanced platform that integrates educational videos with a context-aware chat interface powered by large language models. SAM encourages students to ask questions and explore unclear concepts in real time, offering personalized, context-specific assistance, including explanations of formulas, slides, and images. We evaluated SAM in two studies: one with 25 university students and another with 80 crowdsourced participants, using pre- and post-knowledge tests to compare a group using SAM and a control group. The results demonstrated that SAM users achieved greater knowledge gains specifically for younger learners and individuals in flexible working environments, such as students, supported by a 97.6% accuracy rate in the chatbot's responses. Participants also provided positive feedback on SAM's usability and effectiveness. SAM's proactive approach to learning not only enhances learning outcomes but also empowers students to take full ownership of their educational experience, representing a promising future direction for online learning tools.

Figures (7)

• Figure 1: Structure of SAM, with modification for the user study.
• Figure 2: Example of SAM in action: user submission of an image and formula visualization.
• Figure 3: Implemented modules and their connections in the web application of SAM.
• Figure 4: Representation of the structural elements in the pilot and main studies.
• Figure 5: Exemplary representations from the study.