Analysis And Research To The Data Of CET-4 Score Based On Data Mining

With the expanding of the scale of colleges and universities, and the increase of the number of students, colleges and universities use the various management systems such as student status management, performance management has accumulated a large amount of data. People can only do some simplistic operations to obtain the information on the surface of data, but the information hidden in these large amounts of data has not been fully tap and applied. In this paper, in order to find the main factors influencing the students’ achievements of the CET-4,we are using the data mining technology to mining analysis the performance of the national college English test band 4 (In this paper referred to as the CET-4). Thus provided the scientific basis for teachers to improve English teaching and guide students to learn English, helped students to learn English and review the CET-4 test.1. Mining analysis on college students’achievements of the CET-4 by using the C5.0 algorithm of decision tree classification technology. Firstly, using the data mining tool SPSS Clementine 12.0 to build a decision tree model, effectively prune the decision tree in the process of building it.Then to extract the classification rule. Finally, analyzing and summarizing the classification results. Analysis the influence of CET-4 exam’s three parts (listening, reading, writing) on CET-4’s total score. Thus provided the scientific basis for teachers to improve English teaching and helped students to review the CET-4 test.2. Using k-means algorithm clustering analysis method to analyze the students’CET-4 exams and college English grade point average.According to the clustering results, students are divided into different classes. According to the students’ characteristics of each kind of clustering classes to guide students to learn English and review the CET-4 test, thus improving the students’ exam qualification rate of CET-4.3. Design the factors that affect college students’English level 4 grades questionnaire, using SPSS 19.0 to process the data of questionnaire survey. Results were compared with the data mining analysis, the data mining results were verified, and then synthesize the main factors influencing the CET-4 scores. And put forward the corresponding suggestion from the Angle of teachers and students.In this study, according to the above method to find the reliable factors that affect the students’ CET-4 grades.And these factors have a certain guiding role to teacher’s teaching and to improve the pass rate of CET-4.