Learning Path Analysis of Students Using Data-Driven Approaches for Personalized Learning in E-Learning Management Systems
Zeinab Mostafavi, Tehran University (Iran, Islamic Republic of)
Laurie Shanderson, Founder & CEO @ Accreditation Insights | Higher Education (United States)
Abstract
In the 21st-century educational landscape, personalized learning and data-driven analytics have emerged as transformative approaches to address the diverse needs and learning styles of students in higher education. This study examined the role of student data analytics in enhancing personalized learning experiences in an online learning environment. This study investigates the impact of learning analytics on adaptive learning pathways among 120 university students enrolled in an online program. A purposive sampling method was employed to select the participants. The study utilized a structured questionnaire covering personalized learning dimensions, demographic characteristics, learning needs, and preferences, as well as data extracted from the e-learning management system. These data included key academic performance indicators such as the quality of participation in scholarly discussions, attendance records, and diagnostic and midterm assessment scores. The data analysis involved both descriptive and inferential statistics, with a particular focus on independent and paired t-tests. Grounded in a pragmatist research paradigm, this study adopted a mixed-methods approach that integrated both quantitative and qualitative analyses. The findings revealed that learning analytics can effectively identify students requiring additional support, develop personalized learning pathways, and provide real-time feedback. Moreover, the implementation of adaptive learning technologies and predictive analytics significantly contributes to student engagement and academic performance. All ethical considerations related to data collection, confidentiality, and analysis were strictly observed. The results highlight that not only online universities but also hybrid and traditional institutions must transition towards data-driven education to foster student engagement and enhance learning outcomes. Given the increasing emphasis on personalized learning, this study underscores the necessity of leveraging data analytics as a fundamental tool to improve educational quality and decision-making in higher education.
Keywords |
Data-driven learning, Data analytics, Personalized learning, Adaptive learning |
REFERENCES |
|