Research Article
Data Mining Technology-Based Algorithms for Evaluating English Language Teaching Indicators
@INPROCEEDINGS{10.1007/978-3-031-63130-6_7, author={Wang Qian and Wang Jiaxin and Zhou Huixing}, title={Data Mining Technology-Based Algorithms for Evaluating English Language Teaching Indicators}, proceedings={Application of Big Data, Blockchain, and Internet of Things for Education Informatization. Third EAI International Conference, BigIoT-EDU 2023, August 29-31, 2023, Liuzhou, China, Proceedings, Part I}, proceedings_a={BIGIOT-EDU}, year={2024}, month={7}, keywords={Data Mining English Language Teaching Teaching Indicators Indicator Evaluation}, doi={10.1007/978-3-031-63130-6_7} }- Wang Qian
Wang Jiaxin
Zhou Huixing
Year: 2024
Data Mining Technology-Based Algorithms for Evaluating English Language Teaching Indicators
BIGIOT-EDU
Springer
DOI: 10.1007/978-3-031-63130-6_7
Abstract
TE is a judgement on the value of teachers’ teaching (TT) and students’ learning (SL), and has become an important part of the teaching management and teaching process in universities. There are many common TE systems, most of which evaluate the behavioural performance of teachers, while the learning process and effectiveness of students are rarely mentioned. At the same time, the workflow of implementing TE is tedious and often requires the completion of a large number of data calculation tasks. Therefore how to use modern science and technology to establish a sound, objective and feasible classroom TE system and optimise the evaluation process is an important issue that needs to be addressed urgently. The main objective of this paper is to conduct a study on the evaluation algorithm of English teaching indicators based on data mining (DM) technology. Starting from the construction of a learning-centred university TE system, this paper optimises student TE indicators by using data correlation analysis and association rules. At the same time, machine learning algorithms are introduced into the TE process to build TE models and automate the TE process. Through clustering, the experiment can divide all teachers into corresponding categories, analyse the overall characteristics of teachers in each category, and obtain the performance of teachers in different categories in each indicator, and teachers can focus on their lower level indicators according to the performance of each indicator in their respective categories.
