A Model for Analyzing Students' Mastery of Knowledge Points

Deeply mining the detailed data in the process of students' examination plays an important role in studying students' learning characteristics and realizing individualized learning. Due to the association between test questions mostly given by experts, the number of choosing path length on each question in the process of answering questions can not be accurately collected. In this paper, we propose a model named MASMKP(A Model for Analyzing Students' Mastery of Knowledge Points) based on text analysis in order to combine the examination questions with the knowledge points they belong to. By analyzing the relationship between the questions and combining the number of choosing path length on each question in the process of answering the questions, we can get the students' mastery of the knowledge points. Depending on this model, the text features of test questions are extracted firstly, and the test questions are classified into knowledge points according to the classification model. Then the number of choosing path length on each question is converted to the number of choosing path length on each knowledge point. The number of choosing path length reflects the students' mastery of the knowledge point to a certain extent. Students are clustered according to their mastery of each knowledge point using k-means algorithm, then students with different characteristics are obtained and personalized teaching is realized. The experimental results show that this model can extract and classify the features of students, and the accuracy and validity of this model are verified.