Evaluating English Language Teaching Quality in Classrooms Using OLAP and SVM Algorithms

Abstract

Currently, the existing techniques of evaluating quality of teaching quality colleges and universities within China are based on classical and statistical methods. However, these methods are unable to accurately reflect the real and actual evaluation of teaching quality. Furthermore, in this era of computerization, education has also revamped itself and is not limited to the conventional lecturing approach. Nowadays, English has become one of the most important skills for foreigners as countries move toward internationalization resulting in a huge amount of data being collected in educational databases, which remains unused. Powerful tools are required to improve the quality of English teaching and reap the benefits of big data generated in classrooms. In this paper, online analytical processing (OLAP) in combination with a support vector machine (SVM) classification algorithm is adopted, and then the algorithm constructs the linear optimal decision function in the feature space. Through the training of sample data by the SVM algorithm, relatively high-quality classification results can be obtained on the target object, especially for high-dimensional cases. The proposed approach has an extremely efficient application value. Compared with the existing methods, the error of evaluation results can be greatly improved, which leads to further improvement of accuracy in terms of evaluation results.