Temporal learning analytics based on triple-factor approach using self-organizing map

E-learning personalization aims to deliver learning activities and materials that suits to learners' needs. Therefore, the system must have the ability to analyze the profile and characteristics of each individual learner. Characteristics of learners, among others, can be identified from their behavior in using e-learning. Their most frequent learning resource accessed, their participation on discussions, and their assessment result are some of the variables from the activity logs that can describe their learning patterns. On the other side, learners' behavior may change over time. This research aims to capture and analyze the dynamic learning pattern throughout the semester. The learning analytics are conducted using temporal clustering approach to identify the learning style, motivation, and knowledge abilities. This research performs two-level clustering analysis to acquire learning patterns from activity logs from Moodle Learning Management System using Self-Organizing Map (SOM) and k-Means. SOM enables visualization high dimensional data by projection to lower dimensions. The proto-clusters of SOM are then clustered using k-Means. The temporal clustering results show that the learning patterns of learners are changing over time.