Towards a New Framework of Automatic Detection of Learning Style Based on FSLM

Abstract

AbstractOnline learning environment is defined as new paradigm that has emerged to overcome traditional learning challenges and provides new opportunities. The concept of adaptive educational systems is an increasing research area. Learners tend to have better performances when the course is designed with respect to his/her learning preferences. One most pivotal student’s characteristic is how they prefer to learn. The manner in which individual acquires effectively a new concept is known as learning style approach. In this context, analyzing and detecting students learning styles represents a crucial tool to ensure adaptation in learning management systems. Thus, this research presents an efficient automated approach for detecting learning styles based on Felder Silverman Learning Style Model (FSLSM). We proposed an adaptive placement test based on computerized adaptive testing theory that implements a set of hints driven from FSLSM which assesses principally learners’ prerequisites and then automatically classifies them according to their dominant learning styles.KeywordsAdaptive learningLearning style approachKnowledge levelComputerized adaptive testing theoryFSLSMAutomated methodPlacement test