Social network influence prediction method and device based on graph neural network

Abstract

The invention provides a social network influence prediction method and device based on a graph neural network, and a medium. The method and the device can help a social platform to provide more accurate social content recommendation and friend recommendation for users. The method comprises the following steps: extracting key fields of interaction behaviors from data of a social network platform, and constructing a user global social relation network; sampling to obtain a user local social relation network; splicing the network structure feature and the attribute feature to obtain an initialized feature representation of the user node; according to the interaction frequency in the key field, assigning the adjacent matrix again to obtain a connection strength matrix, and stacking the adjacent matrix and the connection strength matrix to obtain a multi-channel matrix; constructing a graph neural network model comprising a graph convolutional neural network layer and a graph attention neural network layer, and obtaining features of the user nodes learned by the graph neural network model; and constructing a prediction classifier based on the full-connection neural network, and outputting predicted social network influence through the trained prediction classifier.

Description

technical field [0001] The invention belongs to the technical field of network public opinion analysis, in particular to a method and device for predicting social network influence based on a graph neural network. Background technique [0002] With the vigorous development of online social media platforms such as Twitter, Weibo, and Digg, users participate in various online social activities by posting comments, forwarding messages, or voting. Notifications of social activity, and may be influenced to retweet the same message, or vote for the same topic. The industry refers to this phenomenon as online social network influence, which means that a person's emotions, opinions or behavior are influenced by others. Online social network influence has a major impact on the success of social media companies, and it also provides new marketing opportunities for traditional media companies. Therefore, there has been increasing interest in research in developing social influence an...

AI Technical Summary

Problems solved by technology

The result is that existing research methods are insufficient in modeling the connection strength between users, which is helpful for predicting the influence of social networks according to sociological common sense.

Images