LMS cluster data analysis for correcting students' learning

Abstract

This article deals with the analysis of data obtained from databases of learning management systems to organize studentcentred learning with the application of course adaptation methods by changing the set of asynchronous and synchronous learning tools. The relevance of the research in this area is due to the current teaching paradigm as well as the increasing volume of digital data available to universities. The aim of the study is to investigate the possibility of effectively influencing the educational process based on the results of data aggregated from learning management systems (LMS) using cluster analysis. The results of the study confirm the possibility of dividing students into clusters based on their success in perceiving synchronous and asynchronous educational methods, and the effectiveness of corrective impact on the respective clusters of students to improve academic performance. As a conclusion the author made a statement about the effectiveness of practical everyday application of learning analytics aimed at person-centred learning.

Big data processing methods in Learning Management Systems (LMS)

“…The multi-layered structure of the "Big Data LMS" system provides the opportunity to organize versatile software support for the educational environment of the university. Big data LMS" was developed taking into account the basic requirements for web portals (modular architecture; block management; use of presentation templates; separation of access and management of portal users), which creates conditions for using the system as the basis for an educational portal of the university [9,10].…”

Review of Machine Learning Models for Application in Adaptive Learning for Higher Education Student

“…Adaptive learning, which offers the ability to tailor educational materials and pedagogical methods to the needs and abilities of each student, is increasingly becoming significant and sought-after in the educational landscape [1]. Nevertheless, the effective implementation of this approach necessitates developing and applying machine learning models capable of solving complex data analysis and forecasting tasks, considering many related variables [2]. The exploration of machine learning models used in adaptive learning is a pertinent research direction, as the existing models and methods require adaptation and extension for their application within the context of adaptive learning.…”