On using learning analytics to personalise learning

Abstract

The paper aims to analyse possible application of learning analytics / educational data mining (LA / EDM) to support learning personalisation and optimisation in terms of enhancing learning quality and effectiveness. LA / EDM are known as the measurement, collection, analysis, and reporting of data about learners and their contexts, for purposes of understanding and optimising learning and the environments in which it occurs. Researchers, teachers, and policy makers should have a clear idea of what kinds of data, methods, and techniques are needed to optimise learning and its environments. For this purpose, first of all, systematic review of relevant scientific literature on LA / EDM application was conducted. After that, findings of the systematic review concerning possible use and impact of learning analytics on learning personalisation and optimisation are presented. In order to identify scientific methods, tools, techniques and possible results on application of LA / EDM to personalise learning, systematic literature review method devised by Kitchenham has been used. The following research question has been raised to perform systematic literature review: “What are existing LA / EDM methods, tools, and techniques applied to personalise learning?” During the last years (2014- 2016), 519 papers were found in Thomson Reuters Web of Science database on the topic “learning analytics”, including 278 articles, and 174 papers were found on the topic “educational data mining”, including 77 articles. After applying Kitchenham’s systematic review methodology, on the last stage 47 suitable articles were identified to further detailed analysis on the topic “learning analytics”, and 33 – on the topic “educational data mining”. After eliminating duplicating articles, 67 suitable articles were further analysed. Systematic review has shown that, most recently, new data analytics approaches are creating new ways of understanding trends and behaviours in students that can be used to improve learning design, strengthen student retention, provide early warning signals concerning individual students and help to personalise the learner’s experience. Thus, systematic review has shown that LA / EDM could be helpful to personalise learning, but future research is needed in the area, and, first of all, we should clearly identify the main trends concerning application of LA / EDM to personalise learning. Based on systematic review results, the authors have identified the main trends concerning application of LA / EDM to support learning personalisation and optimisation. They are: (1) LA / EDM support self-directed autonomous learning; (2) LA / EDM systems become essential tools of educational management; and (3) most teaching is delegated to computers, and LA / EDM based recommendations will be better and more reliable than those that can be produced by even the besttrained humans. In the paper, an original learning personalisation and optimisation approach based on identification of learners’ needs and application of intelligent technologies is presented. After that, analysis of implementing the aforementioned trends of applying LA / EDM to support learning personalisation and optimisation is provided. This analysis has shown that further development of the authors’ approach on learning personalisation and optimisation is helpful to implement all three aforementioned trends of applying LA / EDM in education.