Optimization and Recommendation System Design of Digital Resources for Civic and Political Education for College Students

In order to realize the personalized recommendation system for college students’ Civic and Political Education, this paper improves the Pearson’s similarity calculation method of traditional recommendation algorithm by adding the popular resource penalty factor and the time decay penalty factor on the basis of resource collaborative filtering hybrid recommendation algorithm, and obtains the resource similarity model of hybrid recommendation algorithm. On this basis, the hybrid recommendation algorithm is used to recommend the learning resources of Civic and Political Education for college students on the online learning platform, and the accuracy and adaptive effect of the hybrid recommendation algorithm are analyzed. The results show that the cumulative hit rate of students increases with the intensity of the recommendation list, and the accuracy rate of active learners is always the highest (97.43%), followed by potential learners (83.77%) and inactive learners (63.16%). The greater the number of videos watched by the three types of college students, the greater the F1 value (88.26%, 77.26% and 43.71%), and the better the model performs. The average difficulty of the educational video resources recommended by the hybrid recommendation algorithm is in line with the students’ own weak ability, and the recommended difficulty is mostly higher than or equal to the difficulty of the actual learning videos. Its recommendation difficulty classification for three types of learners is between 0.1163-0.1399, 0.1163-0.1399 and -0.0173-0.0191, and it is clear that the collaborative filtering hybrid recommendation algorithm model of educational videos recommended by the algorithm proposed in this paper has good adaptability.