By virtue of its ability to adapt to the psychological characteristics of college students, new media has now become a key carrier for the development of Civic and Political Education in colleges and universities. This paper explains the algorithmic recommendation mechanism of new media from multiple perspectives, the opportunities and challenges for college students’ civic education, and proposes a personalized recommendation algorithm for college students’ civic education based on LDA model. On the basis of similarity calculation, a user behavior feature extraction model is established. And combined with the fuzzy C-mean clustering algorithm, the joint information entropy of new media user behavior is calculated, and the joint information entropy results are optimized for the new media recommendation algorithm. Finally, the effectiveness and problems of the new media environment in the ideological and political education of college students are empirically analyzed. The results show that for the new media communication of college students’ Civic and Political Education, 22.04 percent of the students gave a satisfactory answer of 5 points in the content dimension. It shows that in the new media environment, the content of the Civic and Political Education still needs to be constantly innovated, and actively explore the content that is compatible with the physical and mental development and characteristics of college students.