Individualized Customization for Next Generation Virtual Learning Environments
Open Access
- Author:
- Dickens, Bryan R
- Area of Honors:
- Computer Engineering
- Degree:
- Bachelor of Science
- Document Type:
- Thesis
- Thesis Supervisors:
- Conrad S Tucker, Thesis Supervisor
Lee David Coraor, Thesis Honors Advisor - Keywords:
- Virtual Reality
Education Technology
Sentiment Analysis
Data-Mining
Oculus Rift
Immersive Learning - Abstract:
- The brick and mortar classroom environment is the current foundation for learning approaches. However, these environments suffer from two major challenges that make it difficult to achieve individually customized learning for each student. I) the scalability challenge: i.e., the finite size of a classroom and II) the information variability challenge: the variability in the audio and visual content, depending on where a student is seated in a classroom. For these environments, potential solutions exist such as limiting the number of students enrolled in each class, increasing the number of instructors or teaching assistants for each course, or investing in infrastructure or technologies that expand the current capabilities of the physical classroom space. The fundamental research question is how to achieve a consistent, optimized quality of information that is to the expectation of each individual? Virtual Learning Environments (VLEs), such as online classes or immersive simulations, allow for such a scalable learning system because they are based on computational constraints instead of physical constraints. However, these VLEs need to be further explored before they can fully meet the needs of an individualized, customizable learning environment. This work lays the foundation towards addressing this research question by creating a VLE scaled for multiple users in an immersive simulation and demonstrating its benefits, compared to brick and mortar learning. To create that customizable learning at an individual’s personal expertise level, a data-driven methodology is proposed to close the communication gap between a source (i.e., instructor) and a receiver (i.e., student). This work focuses on sensory data emitted by the source and acknowledged by the receiver in addition to sentiment data emitted by the receiver and acknowledged by the source. With statistical analysis, conclusions can be made for each user on these various metrics of the environment to help construct the optimal virtual learning environment for that user.