An analysis of learning analytics in personalised learning.

This paper presents an analysis of learning analytics practices which aimed to achieve personalised learning. It addresses the need for a systematic analysis of the increasing amount of practices of learning analytics which are targeted at personalised learning. The paper summarises and highlights the characteristics and trends in relevant learning analytics practices, and illustrates their relationship with personalised learning. The analysis covers 144 related articles published between 2012 and 2019 collected from Scopus. The learning analytics practices were analysed from the dimensions of what (learning context, learning environment, and data collected), who (stakeholder), why (objective of learning analytics, and personalised learning goal), and how (learning analytics method), as well as their outcomes and limitations. The results show the diversified contexts of learning analytics, with the major ones being tertiary education and online learning. The types of data for learning analytics, which have been increasingly collected from online and emerging learning environments, are mainly related to the learning activities, academic performance, educational background and learning outcomes. The most frequent types of learning analytics objectives and personalised learning goals are enhancing learning experience, providing personal recommendations and satisfying personal learning needs. The learning analytics methods have commonly involved the use of statistical tests, classification, clustering and visualisation techniques. The findings also suggest the areas for future work to address the limitations revealed in the practices, such as investigating more cost-effective ways of offering personalised support, and the transforming role of teachers in personalised learning practices. [ABSTRACT FROM AUTHOR]