A Multilayer Network Approach For Real-Time Adaptive Personalized Learning
Abstract
Traditional classroom instruction provides all students with the same topics, at the same time, at the same speed. However, personalized learning systems that take into account students individual interests, skills, and preferences have been shown to be more effective. Our goal is to develop an adaptive teaching-learning method for enhanced and personalized education, which we call Curated Heuristic Using a Network of Knowledge for Continuum of Learning (CHUNK Learning). CHUNK Learning will provide a curated way of moving through a network of modules composed of educational material joined together by common attributes (i.e., tagged with competency or skill levels). Here, we use a network science approach to develop an initial software prototype, which recommends learning content to students based on their current interests. We establish methods to automatically extract metadata tags to describe course content and student profiles. These tags are used by the software to match courses with individual interests. Moreover, our software is able to simulate student feedback, which helps us test the updating features of our software. This allows us to adapt course recommendations to interest changes throughout the study period and to improve course recommendations for future students. This prototype builds the basis for a CHUNK Learning platform, in which the learner can heuristically discover or learn based on personal background, interests, and skills.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 2018
- Accession Number
- AD1069518
Entities
People
- Jan-daniel Cleven
Organizations
- Naval Postgraduate School