The Multimodal Tutor: Adaptive Feedback from Multimodal Experiences

This doctoral thesis describes the journey of ideation, prototyping and empirical testing of the Multimodal Tutor, a system designed for providing digital feedback that supports psychomotor skills acquisition using learning and multimodal data capturing. The feedback is given in real-time with machine-driven assessment of the learner's task execution. The predictions are tailored by supervised machine learning models trained with human annotated samples. The main contributions of this thesis are: a literature survey on multimodal data for learning, a conceptual model (the Multimodal Learning Analytics Model), a technological framework (the Multimodal Pipeline), a data annotation tool (the Visual Inspection Tool) and a case study in Cardiopulmonary Resuscitation training (CPR Tutor). The CPR Tutor generates real-time, adaptive feedback using kinematic and myographic data and neural networks.