Using Machine Learning Algorithms to Cluster and Analyse Students’ Acceptance of Mobile Learning Management Systems

Aim/Purpose Technology adoption and utilization in educational institutions have increased since the pandemic. Recently, the learning management system has become crucial in the educational sector, enabling the efficient execution of online learning. In this study, we performed clustering on group learners to understand students’ concerns with the mobile Learning Management System (m-LMS) based on the clusters. Furthermore, we employed classification using the technology acceptance model to evaluate the correlation among factors necessitating the acceptance and use of m-LMS. Background Mobile learning (m-learning) is a prevalent method of education where educational content is accessed on the go via mobile devices such as smartphones and tablets. The acceptance and deployment of mobile learning in higher education institutions has become essential in Education 4.0, a reskilling approach associated with Industry 4.0. Since the pandemic, mobile learning management systems have seen increased usage among educational institutions. Methodology The study modified the standard data mining and knowledge discovery methodology. This study’s data set includes 446 students from the University of Education, Winneba, Ghana. The K-means algorithm was implemented to determine the number of clusters from the dataset according to the features. Subsequently, we employed a Pearson correlation coefficient heatmap to ascertain the predictability of perceived ease of use, perceived usefulness, attitude towards using, and actual system use of the features via the technology acceptance model. Then, a classifier was built by comparing five classification algorithms. Contribution A novel study on the application of a machine learning algorithm for a mobile learning management system dataset in Ghana. Implementing K-means, heatmap, and feature selection to understand learners’ concerns while using m-LMS in Ghana. Findings The findings indicate that Cluster 1 members disagree with the benefits of using m-LMS. The disagreement cuts across all the investigated variables: perceived usefulness, perceived ease of use, attitude toward using, and actual use. Cluster 2 members agree strongly with the benefits of using m-LMS across all the investigated variables. Cluster 0, with the highest number of members, moderately agrees with the benefits of using m-LMS. In addition, a strong correlation exists between perceived ease of use, perceived usefulness, and attitude towards using. Furthermore, the attitude towards using was predicted by perceived usefulness. However, there was an unreliable relationship between attitude towards using and actual system use. Recommendations for Practitioners Cluster segmentation of students using m-LMS facilitates the formulation of an implementation policy, enabling educational authorities to address the issues contributing to student dissatisfaction with m-LMS. Furthermore, the results imply that, even though students desire to use a mobile learning management system, they are not using it. It means there are challenges surrounding using the mobile learning management system at the University of Education, Winneba. Recommendations for Researchers The use of K-means, elbow function, and correlation heatmap in the technology acceptance model for variable correlation test reveals detailed predictability patterns that necessitate a new research direction using machine learning. Impact on Society Stakeholders in education should embrace and support machine learning implementation in the educational sector to reveal data patterns for improved teaching and learning. Future Research Subsequent research will broaden the data on mobile learning management systems to include the majority of tertiary institutions in Ghana. The data will be indicative, allowing for the generalisation of inferences regarding national policy directions on m-LMS.