Infrastructure Optimizing through a Big Data Clustering Algorithm-Based Model for Universities' English Online Learning Platform

Abstract

With the improvement of modern information technology and network technology, the construction of online learning platform and English education website is becoming more and more abundant. They provide rich and convenient sources of knowledge for online learners. However, many universitiess and universities do not realize the importance of online teaching mode, and they do not pay enough attention to online teaching in the era of mass data. The present situation of universities English teaching is not optimistic: the quality of English teaching is low, university students' interest in learning is low, and the ideal teaching effect can not be achieved. This is not only due to the deep-rooted traditional concept of teachers in teaching, but also due to the low level of information development of universities education. Based on this, this paper expounds some strategies for the effective construction of universities English online learning platform based on the specific application of mass data in higher education in the current period. Based on data mining technology, this paper makes a correlation analysis and prediction of university students' English education behaviors and achievements, which provides a scientific decision-making basis for English teaching reform and learning in schools. Experiments show that the average error of data clustering in this method is 5.45, while the average errors of LVT and L1 models are 13.18 and 10.37, respectively, which shows that the error rate of big data clustering in this method is low, and its performance is better than that of traditional methods.