Analysis of Lift-apriori-DP Joint Algorithm-based Data Extraction in Business English Achievement in Colleges and Universities

Main Article Content

Hongying Xiao


This paper investigates the application of data mining based on a correlation-rule algorithm in business English performance in colleges and universities. The extracted correlation degree rules are screened by adopting three indexes of support degree confidence degree and lifting degree to measure the correlativity. Experimental validation is carried out on different sets of data sets, and the experimental results show the effectiveness of the Lift-Apriori-DP algorithm. Based on the improved Lift-Apriori-DP algorithm, it is applied to the analysis of students’ performance. Taking the chapter test scores of students in business English courses in colleges and universities as an example, the student’s achievements are extracted and analyzed, and the final appropriate parameter values are selected according to the evaluation of the extraction results under different privacy pre-estimation. The experimental results verify the effectiveness of the Lift-Apriori-DP algorithm in the analysis of student grades and evaluate the accuracy of the algorithm application. The results of this paper show that data mining based on the correlation degree rule algorithm has a wide range of applications in business English grades in colleges and universities, which can provide useful references for teaching and at the same time protect students’ private information from being leaked. In addition, this paper also explores the evaluation class method of the mining results under different privacy pre-estimation, which provides a useful reference for the application of privacy-protecting relevance degree rule mining type algorithms.

Article Details

Special Issue - Scalable Computing in Online and Blended Learning Environments: Challenges and Solutions