Enhancing Student Outcomes through Big Data in Learning Management Systems: A Scoping Review

As digital learning platforms continue to grow at an unprecedented pace, big data technologies are becoming an integral part of Learning Management Systems (LMS). However, the impact of big data on improving LMS to achieve positive student outcomes remains uncertain, necessitating the need for a thorough review. The objective of this scoping review is to examine how big data technologies are applied within LMS and assess their impact on improving student outcomes, focusing on key themes such as predictive analytics, machine learning applications, and the optimization of learning paths. A systematic search was conducted across two databases, identifying ten peer-reviewed studies published between 2015 and 2024. These studies were analyzed to explore the various methods and frameworks used in LMS that incorporate big data analytics. Studies were selected based on relevance to big data and its application in educational settings, particularly LMS. The findings demonstrate that big data significantly contributes to improving student outcomes by enabling predictive analytics for student performance, personalized learning through Educational Data Mining (EDM), and enhancing decision-making in educational management. The reviewed studies also highlight challenges, such as data privacy issues and infrastructure limitations. In conclusion, big data technologies hold substantial promise for transforming LMS and advancing personalized education. However, more research is needed to address challenges and optimize the use of big data for sustained improvements in educational outcomes.

Big Data, Learning Management Systems (LMS), predictive analytics, educational data mining, machine learning in education.