Vilnius Gediminas Technical University (LITHUANIA)
About this paper:
Appears in: ICERI2017 Proceedings
Publication year: 2017
Pages: 3883-3891
ISBN: 978-84-697-6957-7
ISSN: 2340-1095
doi: 10.21125/iceri.2017.1037
Conference name: 10th annual International Conference of Education, Research and Innovation
Dates: 16-18 November, 2017
Location: Seville, Spain
The paper aims to present artificial neural network (ANN) software agent necessary to create personalised adaptive multi-agent learning system. First of all, the authors performed systematic literature review on application of ANN and intelligent program agents to personalise learning in Clarivate Analytics (formerly Thomson Reuters) Web of Science database. The systematic literature review sought to answer the following research question: “How ANN are applied in learning environments to provide and support personalised learning?” After that, methodology of ANN application in a personalised multi-agent learning system is presented. The personalisation in the learning system is based on Felder and Silverman Learning Styles Model. This model requires the use of a questionnaire to determine student’s learning style.

Some students may answer the questionnaire dishonestly or irresponsibly, or make a mistake in self-diagnosis, which results in the creation of an incorrect student’s model. This causes a system to provide suboptimal learning scenarios to the student. The authors present a model of ANN agent to be used in intelligent multi-agent learning system. The proposed software agent uses ANN to associate Felder and Silverman learning styles of students with their behaviour within the learning environment. After training, the agent will identify potentially faulty student models by looking for anomalous behaviour for that learning style. Such situations can be resolved by providing alternative learning scenarios to the students and observing their choices, and by asking the student to complete the questionnaire again.
Artificial neural networks, personalised learning system, intelligent program agent, personalised learning units, learning styles.