Virtual Human Assistants (VHAs) represent a groundbreaking evolution in digital interaction, seamlessly blending advanced natural language processing, expressive facial animations, and lifelike gestures to create immersive, human-like experiences. This study delves into the transformative impact of VHAs on user engagement and learning outcomes by integrating cutting-edge audio-visual elements. Participants will experience three distinct lecture formats: (1) audio-only, (2) audio paired with a VHA face, and (3) audio enhanced by a fully expressive VHA with dynamic facial expressions and body movements. To maximize interactivity and immersion, each lecture incorporates gamified elements, such as real-time, adaptive questioning. Ensuring consistency across all formats, we employ MetaHuman technology within Unreal Engine, delivering realistic, uniform VHAs for a controlled study environment. By fusing VHAs with gamification, this research aims to uncover the optimal synergy of audio and visual stimuli that drives deeper learning, enhances user experience, and reshapes the future of digital education.
