Learning Analytics for Data-Driven Decision Making: Enhancing Instructional Personalization and Student Engagement in Online Higher Education

Introduction

In recent years, the growth and transformation of online education have revolutionized higher education delivery, offering universities and institutions new opportunities for broader access and flexible learning (Al Shehhi & Almarri, 2021; Bozkurt & Sharma, 2022; Dart & Cunningham, 2023; Maseleno et al., 2018; Mathrani et al., 2021; Pargman & McGrath, 2019; Sheikh et al., 2022; Ulfa & Fatawi, 2021; Wong, 2017; Wong et al., 2019; Zhang et al., 2018). However, effectively personalizing instruction and fostering student engagement in the virtual learning environment remain a challenge (Al Shehhi & Almarri, 2021; Dart & Cunningham, 2023; Maseleno et al., 2018; Mathrani et al., 2021).

Learning Analytics (LA), an emerging field combining educational research and data mining, has emerged as a powerful tool in addressing these challenges in online higher education (Bozkurt & Sharma, 2022; Lee et al., 2020; Mathrani et al., 2021; Sheikh et al., 2022; Wise, 2019; Zhang et al., 2018). By leveraging the data generated through online learning platforms, LA provides insights into student behaviours, learning patterns, and performance, enabling informed decision-making, instructional personalization, and improved learning outcomes (Al Shehhi & Almarri, 2021; Al-Tameemi et al., 2020; Banihashem et al., 2022; Bozkurt & Sharma, 2022; Gasevic et al., 2019; Maseleno et al., 2018; Mathrani et al., 2021; Schmitz et al., 2017; Sheikh et al., 2022; Wong et al., 2019; Zhang et al., 2018).

However, the widespread adoption, policy frameworks, and funding initiatives related to LA are still lacking, emphasizing the need for interdisciplinary studies and the integration of technology and pedagogy (Bozkurt & Sharma, 2022; Nouri et al., 2019). The current study aims to explore the application of LA in online higher education, focusing on instructional personalization and student engagement. Through the analysis of data collected from Learning Management System (LMS), including student access, interactions, and course materials, the study seeks to identify patterns and trends that inform instructional design, content delivery, and student support decisions. By advancing LA research, this study contributes to optimizing educational outcomes in the online learning environment.