A log file is used by most e-learning platforms to hold the data collected concerning the learning and teaching activity of the stakeholders. The data gathered needs to be transformed into a helpful form before any decisions can be made. Using educational data mining techniques, one may analyse this data to understand the learning process better and predict their outcomes or early dropout. Simultaneously, it is possible to identify students with similar behavioural patterns. However, students should not be categorized only according to their grades. Instead, their engagement with the educational resources and activities presented within e-learning courses should also be considered. Therefore, this paper presents research in which an unsupervised clustering algorithm is applied to logs to identify groups of students with similar characteristics based on their actions within the context of course data. The most widely used metrics were used to evaluate the proposed clustering model (Silhouette Coefficient, Davies-Bouldin Index, and Calinski-Harabasz Index). A Silhouette score of 0.762 suggests that the clusters are partitioned more effectively, and a Davies-Bouldin score of 0.39 reveals less variance between the clusters. The research results revealed that the k-means clustering algorithm is suitable for identifying students with similar behavioural patterns.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.