OPTIMIZING ADAPTIVE LEARNING USING STATISTICAL AND NETWORK ANALYSIS WITHIN THE CHUNK LEARNING SYSTEM

What can we learn from analyzing how a learner operates within an e-learning system? This research examines an adaptive education system known as CHUNK Learning. This system converts educational material into a network composed of nodes, or CHUNKs of educational content, and edges that represent the connections between some of the nodes. As of now, learners have freedom of maneuver to navigate within the system at their leisure. Each of their actions is a piece of data that can be used by an instructor to comprehend whether a learner is effectively learning or not. The CHUNK Learning system has not yet utilized this valuable data to improve the complex teaching–learning process that occurs in an e-learning environment. We propose a solution to this problem by utilizing user analytics based on two criteria: number of completed educational modules and the number of content views. We conduct two different mathematical approaches based on statistical analysis and network science that allow for a thorough analysis of user data to determine vital trends that enhance the situational awareness of CHUNK Learning. We look to determine user competency scores that may reveal troubling areas of deficiency that may enable instructors to tailor their teaching methods to address each user’s specific needs. In addition, we can further personalize learning to meet user needs by determining the optimal learning content for each course.Captain, United States ArmyApproved for public release. distribution is unlimite