Research on Precision Teaching Strategies of Civic and Political Education for College Students Driven by Big Data

This paper uses big data technology to construct a student portrait model and introduces it into the user-based collaborative filtering algorithm to form a recommendation method for ideological and political education resources, so as to drive colleges and universities to realize the precise teaching of students’ ideological and political education with big data. The K-means clustering algorithm is used to analyze students’ learning behaviors and other characteristic data, and the student portrait is generated according to the constructed student portrait labeling system combined with the results of clustering analysis. The student portraits are fused to calculate the fit between the learning resources of Civic and Political Education and the students, and a final list is generated to recommend to the target students. The K-means algorithm in this paper successfully clusters features of students’ learning behavior, consumption records, and other data. The results of profile coefficient calculation show that the K-means clustering results are reasonable. The accuracy rate of recommending Civics learning resources to students using this paper’s algorithm can reach more than 90.76%, indicating that the resource recommendation method in this paper can effectively realize the personalized recommendation of Civics education resources, and meet the needs of Civics education precision teaching.