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

<p>Big data technology has brought new opportunities for the development of the education industry and can play a positive role in the management of student campus education. In this paper, the behavioral features in the extracted multi-source behavioral data of college students are dimensionality reduced using principal component analysis, and the behavioral features are clustered using density peak clustering and undersampling methods. The Adaboost algorithm is used to identify and classify each behavioral feature to obtain behavioral analysis data for students. Finally, the university’s education management system is constructed based on this behavioral analysis model. The behavioral analysis of students in a university shows that both consumption behavior and book borrowing behavior cluster into three categories. Among them, the type of students who clocked into the library with a medium frequency and borrowed the most number of books had the highest percentage (39.25%) among the students in this university. And there is about a 79.3% probability that students of the university with a high number of absences seldom visit the library. The study also showed that there was a significant difference (p&lt;0.05) in the study behavior of students in both experimental and control classes after the application of the educational management system. The student behavior analysis and management platform proposed in this paper effectively promotes the development and progress of education management in colleges and universities and improves the efficiency of student management work and the scientificity and reliability of the results.</p>
</abstract>

Big data technology has brought new opportunities for the development of the education industry and can play a positive role in the management of student campus education. In this paper, the behavioral features in the extracted multi-source behavioral data of college students are dimensionality reduced using principal component analysis, and the behavioral features are clustered using density peak clustering and undersampling methods. The Adaboost algorithm is used to identify and classify each behavioral feature to obtain behavioral analysis data for students. Finally, the university’s education management system is constructed based on this behavioral analysis model. The behavioral analysis of students in a university shows that both consumption behavior and book borrowing behavior cluster into three categories. Among them, the type of students who clocked into the library with a medium frequency and borrowed the most number of books had the highest percentage (39.25%) among the students in this university. And there is about a 79.3% probability that students of the university with a high number of absences seldom visit the library. The study also showed that there was a significant difference (p<0.05) in the study behavior of students in both experimental and control classes after the application of the educational management system. The student behavior analysis and management platform proposed in this paper effectively promotes the development and progress of education management in colleges and universities and improves the efficiency of student management work and the scientificity and reliability of the results.

Behavioral Analysis and Educational Management of College Students in Universities by Integrating Multi-source Data

Applied Mathematics and Nonlinear Sciences

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

Big data technology has brought new opportunities for the development of the education industry and can play a positive role in the management of student...

Behavioral Analysis and Educational Management of College Students in Universities by Integrating Multi-source Data

Publicado en línea: 05 ago 2024

Páginas: -

Recibido: 26 mar 2024

Aceptado: 24 jun 2024

DOI: https://doi.org/10.2478/amns-2024-2237

Palabras clave
Behavioral characteristics, PCA algorithm, Cluster analysis, Adaboost algorithm, Education management

© 2024 Xiangpu Xu, published by Sciendo

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

Behavioral Analysis and Educational Management of College Students in Universities by Integrating Multi-source Data

Publicado en línea: 05 ago 2024

Páginas: -

Recibido: 26 mar 2024

Aceptado: 24 jun 2024

DOI: https://doi.org/10.2478/amns-2024-2237

Palabras claveBehavioral characteristics, PCA algorithm, Cluster analysis, Adaboost algorithm, Education management

© 2024 Xiangpu Xu, published by Sciendo

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

Palabras clave
Behavioral characteristics, PCA algorithm, Cluster analysis, Adaboost algorithm, Education management