Learning content personalization based on triple-factor learning type approach in e-learning

Abstract

One of the emerging issue in e-learning is to create adaptive learning based on learner's perspective. Adaptive learning can be realized through personalization of e-learning. Personalized learning help learners to use their best performance in order to reach learning goals based on their needs, preferences, and characteristics. To accomodate different characteristics of the learners, learning content personalization system based on triple-factor learning type was developed. The characteristics of 36 triple-factor learning type were used as input for learning content personalization algorithm to produce learning content that suitable for the learners's learning type. The algorithm implemented into a system which called SCELE-Personalization Dynamic E-learning. The system was used by 118 learners in Science Writing course at the Faculty of Computer Science, Universitas Indonesia as experimental group. In order to find the best learning performance, the exam score from experiment group were compared with the exam score from control group. The result shows learning performance of experimental group that used personalized learning feature is better than learning performance of control group who used non-personalized learning feature. It can be seen from significant value (p<;0,05) and the different mean score of the experimental group that reach 13,68.