Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.732347
Title: An agent-based architecture to support adaptivity in virtual learning environments based on learners' learning styles
Author: Al-Omari, Mohammad
ISNI:       0000 0004 6496 698X
Awarding Body: De Montfort University
Current Institution: De Montfort University
Date of Award: 2017
Availability of Full Text:
Access from EThOS:
Access from Institution:
Abstract:
Educational systems have been improving as a result of the revolution in technology. Learning Management Systems (LMSs) are becoming crucial and widely used in many educational institutions for the adoption of blended and distance learning. However, a “one-size-fits-all” approach is the basis of most of these systems, whereby differences and preferences such as the knowledge level and learning styles of learners are not taken into consideration in their design. Current e-learning systems are unable to provide learners with adaptive content that meets their learning styles preferences. This thesis aims to extend the capabilities of LMSs to support adaptivity based on learners’ learning styles. Therefore, a hybrid architecture design is proposed reflecting a novel approach in order to support dynamic real-time adaptivity in any LMS based on learners’ learning styles. The architecture is designed based on a computational model using the technology of intelligent agents and the concept of the Event-Condition- Action (ECA) model. The proposed approach introduces a real-time dynamic adaptation process that follows specific adaptive features, namely, the type, number and order of the presented contents. These adaptive features are based on the recommendations of the Felder-Silverman Learning Styles Model. A system prototype of the approach is developed and integrated in an e-learning environment (i.e. Moodle). Finally, the proposed approach is evaluated using a case study in Moodle.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.732347  DOI: Not available
Share: