A model for learning analytics to support personalization in higher education

Abelardo Pardo, Negin Mirriahi, Dragan Gašević, Shane Dawson

Research output: Chapter in Book/Report/Conference proceedingChapter (Book)Researchpeer-review

2 Citations (Scopus)

Abstract

Digital higher education continues its evolution towards a wider use of technology to support learning experiences. The global pandemic has elevated new sets of educational challenges that highlight the importance of technology as a critical component of contemporary education systems. However, reliance on technology also raises concerns about sustaining support in these new modes of delivery while effectively promoting the attainment of learning objectives. Learning analytics offers the possibility of supporting designers and educators to gain a deeper understanding of how learners are engaging and progressing in their learning process. Increased understanding opens the door to a higher level of personalization to meet the diverse range of learners. However, achieving this connection between comprehensive data sets and personalization requires the combination of design, delivery and analytics and the participation of various stakeholder groups. This chapter presents the conceptual Learning Analytics Model for Personalization (LAMP) to represent the relationships between the elements in a digital learning experience with comprehensive data capture and personalized learner support actions. The model is showcased in the context of the provision of personalized learner feedback.

Original languageEnglish
Title of host publicationHandbook of Digital Higher Education
EditorsRhona Sharpe, Sue Bennett, Tünde Varga-Atkins
Place of PublicationCheltenham Glos UK
PublisherEdward Elgar Publishing
Chapter3
Pages26-37
Number of pages12
Edition1st
ISBN (Electronic)9781800888494
ISBN (Print)9781800888487
Publication statusPublished - 2022

Cite this