An Open Learning Design, Data Analytics and Visualization Framework for E-Learning
The aim of this project is to serve MOOC instructors, instructional designers, institutional curriculum leaders and learning scientists by developing an open framework that integrates three major E-learning technology components:
- Learning and assessment design models and tools that guide and support E-learning course design and the advance planning of specific learning analytics and evaluation requirements;
- Analytical methods, including learning behavior analysis and predictive analytics, for facilitating personalization of online learning and improving the retention rate of MOOC courses;
- Visualization interfaces for understanding the huge amount of data collected by MOOC platforms and the analytical results.
An open source instantiation of the framework will be developed and pilot studies with multiple real MOOCs and blended courses will be conducted at Hong Kong University of Science and Technology, MIT, and the University of Hong Kong. The outcomes of this project include a novel approach and suite of tools for E-learning design, tested models of pedagogical and assessment designs for E-learning, new analytics and data visualization methods for learning behavior analysis and prediction, a comprehensive open source system for MOOC course design and data analytics, and new findings on E-learning from the multi-university pilot studies.
Plan to Phase II
Phase 2 (Y3-Y4) of this project aims to facilitate K-12 and MOOC instruction and research by:
- Developing open-source analytical and visualization methods for K-12 resource-based e-learning in mathematics;
- Articulating design patterns in integrated learning and analytics for computational thinking (CT) in MOOCs and K-12;
- Evaluating (1) and (2) on a pilot scale.
Analytical and visualization methods are targeted because e-learning in K-12 education is often centered around resources such as item banks and videos, but these platforms lack students' interaction data in test items, limiting the possibility of further data analytics. CT and mathematics are both important areas in STEM education. CT is a key 21st century competence encompassing knowledge, skills and their application to solve problems. The integrated patterns will provide data-driven feedback to inform e-learning design.