Automatically difficulty grading method of "instruction system" question bank based on knowledge tree

The aim of this study is to propose a model, which can automatically grade difficulty for a question from "Instruction System" question bank. The system mainly uses attributes which are employed to be input. A knowledge tree model which was established based on the proper nouns from Chinese "Instruction System" teaching material and a machine learning algorithm are utilized as important parts for classification. The experimental dataset comes from our built "Principles of Computer Organization" online education system, the accuracy result of difficulty classification could be 79.41% which is much higher than the accuracy of random guess 50%.