A Personalized Genetic Algorithm Approach for Test Sheet Assembling

In recent years, computer-aided test-sheet composition has become an effective method to evaluate students' learning level. To meet the needs of personalized test-sheet assembling for every student, a new test-sheet construction model is proposed. Based on the model, a personalized genetic algorithm (PGA) is proposed to assemble appropriate test sheets for individual students according to their different levels in mastered concepts of subjects. The proposed approach incorporates personalized information as preference gene bit into the crossover operator of genetic algorithm and fitness function, so as to select more non-mastered questions in the final test. In the experiments, the proposed algorithm was applied to assemble a series of items for students and the results demonstrate that the proposed approach is capable of effectively assembling personalized test sheets that meet the needs of different students and achieve good performance.