Realistic Challenges and Optimization Approaches of Civic Education in Colleges and Universities in the Context of Big Data

Abstract

Abstract Civic and political education with big data should not just be a one-way knowledge inculcation. It is more of a guideline and direction that can guide everyone’s life. This paper gives a detailed description of the realistic challenges facing Civic and Political Education in the context of big data and gives the optimization path of Civic and Political Education in combination with big data technology. The essence of ideological education is to help students establish correct concepts and values of life. This paper uses the PSO algorithm to improve the K-means algorithm, builds a student portrait based on student data, and fully analyzes the behavior related to student life consumption. Then, through the FOA algorithm to optimize the parameters of the SVM algorithm, the student learning data for deep mining in order to achieve the student academic early warning, to help college administrators understand the student learning situation. The purpose of Civic Education is to aid students in establishing correct concepts of life and learning, and this paper conducts corresponding empirical analysis. The results show that the PSOK-means algorithm achieves absolute convergence after 45 iterations, and its MSE value is 2.208, the FOA-SVM algorithm has 0.0979s more computing time than the RF-SVM algorithm after 2000 iterations, and the clustering of students’ portraits results in 4 classes, and the accuracy of academic warning is more than 80%. Reasonable big data technology and the deep integration of the application of political education in colleges and universities can help college administrators understand the development of students so as to formulate a political education program that is more in line with the development of students and to improve the quality of talent cultivation in colleges and universities.