<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This paper adopts a nonlinear support vector machine to categorize the information on students’ ideology and politics in colleges and universities, and completes the construction of a dynamic early warning mechanism for ideology and politics education. Firstly, it builds the early warning system, establishes the students’ civic and political information file, designs the user information module of the system, then sets the index system according to the opinions of the civic and political teachers in colleges and universities, and designs the civic and political dynamics early warning module based on this. Following the completion of the design, four groups of tests were conducted. Colleges A and B were used to implement the system for individual testing, followed by early warning testing using data from multiple colleges simultaneously. Finally, the most significant indicators were tested using group condition analysis. The various tests show that the system response speed is 322ms, which is lower than the industry requirement of 1s. Among the three metrics tested, the system accuracy of this paper is the highest, at 87.2%, 88.1%, and 80.7%, respectively. The X5 scores of 87.56% of the students in each university were generally low, in the range of 1 to 2, indicating that the students were not clear about the importance of the Civics program, but the X12 scores of 94.52% of the students were high, indicating that they believed that the Civics program should be retained. Obtaining a high level of Civics education is made possible by achieving a mission responsibility consistency score of 0.865.</p>
</abstract>

This paper adopts a nonlinear support vector machine to categorize the information on students’ ideology and politics in colleges and universities, and completes the construction of a dynamic early warning mechanism for ideology and politics education. Firstly, it builds the early warning system, establishes the students’ civic and political information file, designs the user information module of the system, then sets the index system according to the opinions of the civic and political teachers in colleges and universities, and designs the civic and political dynamics early warning module based on this. Following the completion of the design, four groups of tests were conducted. Colleges A and B were used to implement the system for individual testing, followed by early warning testing using data from multiple colleges simultaneously. Finally, the most significant indicators were tested using group condition analysis. The various tests show that the system response speed is 322ms, which is lower than the industry requirement of 1s. Among the three metrics tested, the system accuracy of this paper is the highest, at 87.2%, 88.1%, and 80.7%, respectively. The X5 scores of 87.56% of the students in each university were generally low, in the range of 1 to 2, indicating that the students were not clear about the importance of the Civics program, but the X12 scores of 94.52% of the students were high, indicating that they believed that the Civics program should be retained. Obtaining a high level of Civics education is made possible by achieving a mission responsibility consistency score of 0.865.

Construction of Dynamic Early Warning Mechanism for Civic Education in Colleges and Universities Based on Data Mining

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

This paper adopts a nonlinear support vector machine to categorize the information on students’ ideology and politics in colleges and universities, and...

Construction of Dynamic Early Warning Mechanism for Civic Education in Colleges and Universities Based on Data Mining

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 15. Dez. 2023

Akzeptiert: 25. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0112

Schlüsselwörter
Data mining, Nonlinear support vector machine, Early warning system, Civic education

© 2024 Mingna Yang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Construction of Dynamic Early Warning Mechanism for Civic Education in Colleges and Universities Based on Data Mining

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 15. Dez. 2023

Akzeptiert: 25. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0112

SchlüsselwörterData mining, Nonlinear support vector machine, Early warning system, Civic education

© 2024 Mingna Yang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Data mining, Nonlinear support vector machine, Early warning system, Civic education