Research Article
Research on Rapid Selection of University Funding Objects Based on Social Big Data Analysis
@INPROCEEDINGS{10.1007/978-3-031-50543-0_30, author={Xiaoyan Xu and Yuliang Zhang}, title={Research on Rapid Selection of University Funding Objects Based on Social Big Data Analysis}, proceedings={Advanced Hybrid Information Processing. 7th EAI International Conference, ADHIP 2023, Harbin, China, September 22-24, 2023, Proceedings, Part I}, proceedings_a={ADHIP}, year={2024}, month={3}, keywords={Big Data Analysis Means Colleges and Universities Quick Selection Social Big Data Funding Target.}, doi={10.1007/978-3-031-50543-0_30} }- Xiaoyan Xu
Yuliang Zhang
Year: 2024
Research on Rapid Selection of University Funding Objects Based on Social Big Data Analysis
ADHIP
Springer
DOI: 10.1007/978-3-031-50543-0_30
Abstract
With the sharp increase in the number of college students, the number of students who need financial aid also increases.How to quickly and accurately select university funding objects has become the key to achieve the goal of funding education. Therefore, this paper proposes a research on rapid selection methods of university funding objects based on social big data analysis. Based on the principles of systematicness, objectivity, scientificity and feasibility, we will build an index system for the selection of university funding objects, deeply mine the index data for the selection of university funding objects in the big data of social communications, build a pre-processing framework for the selection of index data, re sample the index data for the selection of university funding objects based on the SMOTE algorithm, and eliminate the adverse effects of unbalanced data. Set up a model for selecting university funding objects, formulate rules for selecting university funding objects, and realize rapid selection of university funding objects. The experimental results show that after the application of the proposed method, the corresponding maximum accuracy rate of the selection results of university funding objects is 98%, the maximum recall rate is 91%, and the maximum F value is 0.96, which fully confirms that the proposed method has better application performance.
