Abstract:
In traditional community detection algorithms, the similarity of network nodes is usually measured by spatial distance, which is not easy to understand or can only be explained from the perspective of distance. This paper proposes a spectral clustering method based on the similarity of text content, which measures the attribute similarity of network nodes by the similarity of text information of users in the network community, and makes the attribute connection of nodes more meaningful when considering the network structure. On this basis, the idea of spectral clustering is used to divide the community. The experimental results show that the modular degree and the average similarity of nodes are high, and the clustering effect is good.