Multimodal Data Mining and Learning Behavior Analysis for Civic Education

This paper designs a multimodal data mining and learning behavior analysis model for civic education, uses improved clustering and association rule algorithms to analyze the multimodal data obtained from students, mines the basic consumption, learning and life behavior characteristics, and carries out analysis of the students’ civic situation in order to take targeted civic education measures. Aiming at the problem that traditional clustering results are greatly affected by the selection of initial clustering centers, Gaussian density function is used to determine the initial clustering centers, and Euclidean distance is replaced by density-sensitive distance to avoid sensitivity to noise and anomalies, which improves the accuracy of the clustering results of students’ behaviors. Then we use the FP-Growth association rule algorithm to improve the Apriori construction, recursively and iteratively construct the frequent pattern tree and get the final frequent item set, which improves the efficiency of student behavior data mining. After analyzing the processed student data of a university, it is found that most of the students have low interest in borrowing books, 38.22% of the students borrowed only 2.19 books on average, and the total number of times of book borrowing is only 5.4 times, and the average number of days of single borrowing is 62.3 days, and the school library needs to increase the promotion of students’ reading, which can be done through the way of offline book fairs and e-recommendations to improve students’ interest in reading books. Reading interest. The study makes a useful exploration for the informatization and intelligentization of ideological education in colleges and universities.