Automated Test Assembly with Minimum Redundant Questions Based on Bee Algorithm

Abstract

An ideal test form should contain questions with different level of difficulties and non-redundant questions. This paper proposed an automated test assembly algorithm to minimize the redundant question in a test form based on Bee algorithm. A neighborhood search in Bee algorithm is improved by using a new technique, called Min-SumDistance (MSD). The MSD is the distance of considered question compared to others in the test form. The sum of question pairs distance indicates to the redundant question in the test form. A question content is represented in two forms as an unigram with TF and TF-IDF scores. The experiments using 200 questions from Information Technology Professional Examination(ITPE). To evaluate the performance of MSD method, we count a number of enemy pairs of the test form and compared to the random method. The experimental results show that our proposed algorithm yields the significant numbers of redundant questions.