Granular Mining of Student's Learning Behavior in Learning Management System Using Rough Set Technique

Pattern multiplicity of user interaction in learning management system can be intelligently examined to diagnose students’ learning style. Such patterns include the way the user navigate, the choice of the link provided in the system, the preferences of type of learning material, and the usage of the tool provided in the system. In this study, we propose mapping development of student characteristics into Integrated Felder Silverman (IFS) learning style dimensions. Four learning dimensions in Felder Silverman model are incorporated to map the student characteristics into sixteen learning styles. Subsequently, by employing rough set technique, twenty attributes have been selected for mapping principle. However, rough set generates a large number of rules that might have redundancy and irrelevant. Hence, in this study, we assess and mining the most significant IFS rules for user behavior by filtering these irrelevant rules. The assessments of the rules are executed by evaluating the rules support, the rules length and the accuracy. The irrelevant rules are further filtered by measuring different rules support, rules length and rules accuracy. It is scrutinized that the rules with the length in between [4,8], and the rules support in the range of [6,43] succumb the highest accuracy with 96.62%.