Application of artificial neural networks to support personalised learning

Abstract

The paper aims to analyse possible application of artificial neural networks (ANNs) to support learning personalisation and optimisation in terms of enhancing learning quality and effectiveness. ANNs are referred here as a computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs. Information that flows through the network affects the structure of the ANN because a neural network changes – or learns, in a sense – based on that input and output. An ANN has several advantages but one of the most recognised of these is the fact that it can actually learn from observing data sets. In the paper, first of all, systematic review was performed in Clarivate Analytics (formerly Thomson Reuters) Web of Science database. The following research question has been raised to perform systematic literature review: “What are existing ANN methods, tools, and techniques applied to support personalised learning?” During XXI century (2001-2017), 100 articles in English were found in Web of Science database on the topic “TS=(artificial neural network* AND education)”. After applying Kitchenham’s systematic review methodology, on the last stage 20 suitable articles were identified to further detailed analysis on possible application of ANN to support personalised learning both in general and Higher education. Systematic review has shown that ANNs are already quite actively used in both school and University education to solve different problems e.g. academic assessment, predicting students’ success and dropout, predicting instructional effectiveness of virtual learning environments, performance evaluation of online teaching and learning, improving students’ motivation, analysing emotional social and cognitive competencies, modelling student cognitive processes, cognitive diagnostic, course timetabling etc. At the same time, ANNs are still rarely used to personalise learning according to students’ needs, and future research is needed in the area. After that, the author’s original learning personalisation methodology based on identifying students’ learning styles and other needs is presented in more detail. The last but not the least, some insights on possible application of ANN to support personalised learning are provided. This should be helpful to enhance learning quality and effectiveness.