This paper combines multi-source data and obtains effective data collection with higher value and richer knowledge connotations by cleaning, integrating, filtering, and transforming the original data. It also calculates the propagation characteristics of new media innovation, proposes the similarity of nodes, combines the propagation probability to construct the centrality degree and the near centrality expression, and analyzes the relationship of the propagation term that affects the new media innovation. The results show that when p takes 0.1, it is 13.8 and 14.15 seconds at 100 nodes and 500 nodes of new media innovations, indicating that the propagation time starts to extend gradually with the increase of p-value. The correlation between dissemination power and time in new media innovation incorporating multi-source data is demonstrated.