Personalized item generation method for adaptive testing systems

Abstract

An Intelligent Tutoring System (ITS) must provide suitable feedback to learners based on tests adapted to the learners' ability levels. An ITS selects the item and content based on what it knows about the learners from previous items. Previous research has focused on estimating a learner's ability accurately or providing adequate feedback based on an analysis of the learner's ability. However, it is often difficult to make customized learning continuously available in ITSs. In the present study, we used adaptive testing to estimate a learner's ability and to determine a number of learner characteristics to create a learner profile. This method selects items and creates a customized assessment sheet for adaptive testing that considers both the learner's level and characteristics. The proposed method assesses a learner's weak subject areas and item types by studying available information and analyzing individual abilities to guide learners as to which fields of study would be suitable and which courses they should take. We tested our customized learning module at an actual educational institution. The group that used our recommendation module learned more effectively than the control group (the mean test scores of the group that used the module were high and the deviations were low). Using the learner model, teachers will be able to analyze learners in detail, enabling customized learning that allows learners to study effectively without requiring a great effort to search for learning materials. Customized learning will increase interest in learning and understanding.