Test Sheet Generation Using Feasible Item First Genetic Algorithm

Abstract

In a computer-assisted testing system, the quality of the test items will significantly affect the accuracy of the test. Selection of appropriate test items is important when constructing a test-sheet that meets multiple assessment requirements such as, average difficulty degree, average discrimination degree, length of the test time, number of the test items and specified distribution of the concept weights. A good test will not only help the instructor evaluate the learning status of the students, but also facilitate the diagnosis of the problems embedded in the students’ learning process. A approximation method based upon a genetic approach has been developed. Statistics from a series of computational experiments indicate that our approach is able to efficiently generate near-optimal combinations of test items that satisfy the specified requirements or constraints.