An Adaptive, Structure-Aware Intelligent Tutoring System for Learning Management Systems
Sebastian Kucharski, Iris Braun, Tommy Kubica · 2023
Intelligent Tutoring Systems (ITS) can be used to provide personalized assistance in Learning Management Systems (LMS). The main drawbacks to this end are that they are usually self-contained or system-dependent, and that integrations often lack in a representation of the considered learning content structure (i.e., are not structure-aware). The former prevents the reuse of devised didactic concept implementations. The latter can cause the user to get lost during the guidance process. Both are challenging to overcome because of the heterogeneous, LMS-specific approaches to structuring learning content. The aim of this thesis is to investigate frame conditions for reusing structure-aware ITS functionalities across LMS and to illustrate the gained insights in an elaborated ITS. Therefore, a system architecture is proposed that can retrieve the required learning process data from an LMS by employing a thin adaptation layer and transform this data into a generic data structure. This structure is used for providing assistance and for generating and integrating the learning content structure representation. The focus of this thesis is on the system-independent implementation of structure-aware intelligent assistance scenarios. The approach will be evaluated in terms of applicability and effectiveness considering different state-of-the-art LMS.