Association analysis for an online education system

An important goal of data mining is to discover the unobvious relationships among the objects in a data set. Web-based educational systems collect vast amounts of data on user patterns, and data mining methods can be applied to these databases to discover interesting associations between student attributes, problem attributes, and solution strategies. In this paper, we propose a framework for the discovery of interesting association rules within a Web-based educational system. A hybrid measure of subjective and objective measure for rule interestingness is proposed which is called contrasting rules. Contrasting association rule is one in which a conjunction of attributes is compared for complementary subsections of a data set. We provide a new algorithm for mining contrasting rules that can improve these systems for both teachers and students - allowing for greater learner improvement and more effective evaluation of the learning process. A larger advantage of developing this approach is its wide application in any other data mining application.