A proposed dynamic technique for detecting learning style using literature based approach

Abstract

This paper describes a dynamic technique for identifying learners learning styles based on their behavior in the learning environment influenced by literature approach. The technique was suggested based on VAK Learning Styles model and the behavioral patterns. First we defined the learning material features (contents, case studies, examples, exercises and assessments) and the behavioral patterns (staying time, visits, and answers); then we connected these features and patterns with the VAK learning styles determining the effect of each learning style on each pattern. Then, we applied some general rules and algorithms to estimate the learning style. We prepared a pilot e-learning environment to test and validate the proposed technique, the estimated learning styles from the detection module in the learning environment were compared to the results of a VAK questionnaire; which learners answered before entering the learning environment, the behavior patterns of eighteen participants in the pilot environment were monitored in order to estimate the learning style, eight were detected correctly, four balanced and seven in-correctly, the accuracy of the system was measured to about 52.78 %.