Mathematical Modeling and Simulation of Online Teaching Effect Evaluation Based on Decision Tree Algorithm

Abstract

With the support of big data technology, the field of education is also facing new problems and opportunities. Network teaching has become the mainstream means of higher education. In order to explore the changes of students’ learning effect in the process of online teaching, this paper proposes to build an online teaching effect evaluation model with the support of data mining technology and decision tree algorithm. This paper records the factors and objects that reflect the teaching effect in network teaching and traditional teaching, respectively. A decision tree algorithm is used to divide the attributes of influencing factors from relevant rules. Using the Kirschner model to build the evaluation system, add two attribute elements: students’ teaching evaluation and teachers’ self-evaluation. Data mining technology is used to preprocess and clean up the sample set, which improves the accuracy of the calculation results. In the evaluation model, the association rule algorithm is also constructed to classify the data of the same element type and delete the data of different elements after marking. Through this evaluation model, teachers can accurately judge students’ learning interests and improve students’ academic performance. The results show that compared with the traditional data mining algorithm, the decision tree algorithm has obvious advantages in computing speed and accuracy.