Content dissemination strategy of political ideological education in colleges and universities under the new media environment

Abstract

New media technology can provide powerful support for the dissemination of political and ideological education content in colleges and universities. This paper relies on the hybrid recommendation algorithm to construct a personalized recommendation system for ideological and political education content in colleges and universities, which provides a brand new strategy for the dissemination of ideological and political education content. The popular resource penalty factor and time decay penalty factor are introduced into the original Pearson similarity calculation to improve the accuracy of the recommendation algorithm. This paper employs the statistical analysis method to examine the influence of the personalized recommendation system on the spread of ideological and political content in colleges and universities. The big data analysis module in the system predicts users’ forwarding behavior and the system’s dissemination effect, while the SIR model, which incorporates forwarding probability, conducts simulation experiments to replicate users’ ability to disseminate information. It has been found that the vividness, originality, interactivity, and interestingness of the recommended content of the system have a significant impact on the number of user likes and positive comments, which measure the dissemination effect. The big data analysis module is able to predict the forwarding behavior of users and the depth of dissemination of civic and political education content with accuracy exceeding 90% and 80%, respectively. Simultaneously, the system’s core users disseminate civic and political education content quickly and widely, allowing the system to effectively disseminate these contents in this paper.

Keywords

• hybrid recommendation algorithm
• penalty factor
• sir model
• new media technology
• 97m80