Home // HUSO 2019, The Fifth International Conference on Human and Social Analytics // View article
Adaptive Personalized Network Relationships in the CHUNK Learning Environment
Authors:
Shane Smith
Maria Smith
Mario Andriulli
Ralucca Gera
Michelle Isenhour
Keywords: education; adaptive learning; learning systems; network theory (graphs); adaptive algorithms
Abstract:
How can learner profiles support personalized online learning? Our current research analyzes a personalized adaptive system for education called CHUNK Learning. The CHUNK Learning system builds on a network of modules, and a learner profile, both tagged with keywords. CHUNK Learning currently utilizes simple keyword relationships to suggest a tailored, personalized, adaptive learning plan guiding the learner through the network of modules. However, supervised machine learning methods may be more suitable to enable the implementation of an iterative algorithm for refined learning plans. In this paper, we investigate the relationship between learner profile and adaptive learning plans. Learners first create a profile in CHUNK Learning which establishes their baseline learning plan. Then, as learners begin to interact with the learning environment, the CHUNK Learning system updates the learning plan based on learner activities (learned, viewed, tested), keyword searches, and content ratings by increasing or reducing the strength of the connection between the learner profile and activities. Additionally, we demonstrate that by connecting all learners within an academic program, we create a stronger bond between learners, which results in a reduced path between activities. We conclude that by reducing the path length between activities, we strengthen connections in the CHUNK Learning environment.
Pages: 80 to 88
Copyright: Copyright (c) The Government of USA, 2019. Used by permission to IARIA.
Publication date: June 30, 2019
Published in: conference
ISSN: 2519-8351
ISBN: 978-1-61208-725-2
Location: Rome, Italy
Dates: from June 30, 2019 to July 4, 2019