E-Learners’ Activity Categorization Based on Their Learning Styles Using ART Family Neural Network

Adaptive learning means providing the most appropriate learning materials and strategies considering students' characteristics. Grouping students based on their learning styles is one of the approaches which has been followed in this area. In this paper, we introduce a mechanism in which learners are divided into some categories according to their behavioral factors and interactions with the system in order to adopt the most appropriate recommendations. In the proposed approach, learners' grouping is done using ART neural network variants including Fuzzy ART, ART ۲A, ART ۲A-C and ART ۲A-E. The clustering task is performed considering some features of learner's behavior chosen based on their learning style. Additionally, these networks identifythe number of students' categories according to the similarities among their actions during the learning processautomatically. Having employed mentioned methods in a web-based educational system and analyzed their clustering accuracy and performance, we achieved remarkable outcomes as presented in this paper.

Keywords:

Personalized e-Learning System , Adaptive Resonance Theory , ART Neural Network , Learning Style , Intelligent Tutoring System