Home // eLmL 2023, The Fifteenth International Conference on Mobile, Hybrid, and On-line Learning // View article

Architectural Design of an Adaptive, Structure-Aware Intelligent Tutoring System

Authors:
Sebastian Kucharski
Tommy Kubica
Iris Braun

Keywords: personalized learning; technology-enhanced learning; learning analytics; educational data mining

Abstract:
Intelligent Tutoring Systems (ITS) for Learning Management Systems (LMS) combine the benefits of user-centered learning and the provisioning of easy-to-use learning content in one place. They typically have two major drawbacks. First, they are LMS-specific (i.e., not adaptive). Thus, many LMS do not include an ITS because existing solutions cannot be reused. Second, they lack in a didactically usable representation of the structure of the learning content (i.e., they are not structure-aware). Therefore, the learner may get lost during the provision of assistance. Overcoming both of these drawbacks at once is a desirable objective, because it allows the learner to take advantage of personalized learning in diverse LMS while accessing a large amount of available learning content. In addition, it allows an ITS to use cross-plattform analytics (CPA) to improve assistance. The main challenge in achieving this objective is dealing with the heterogeneous approaches to structuring learning content used by different LMS. For this purpose, an adaptive, structure-aware ITS is proposed that can work with diverse LMS by using a generic data structure that can represent and process the required learning knowledge data in a system-independent way. The focus of this paper is to outline the architecture of this system.

Pages: 41 to 43

Copyright: Copyright (c) IARIA, 2023

Publication date: April 24, 2023

Published in: conference

ISSN: 2308-4367

ISBN: 978-1-68558-081-0

Location: Venice, Italy

Dates: from April 24, 2023 to April 28, 2023