Superedge prediction: What opinions will be mined based on an opinion supernetwork model?

作者:

Highlights:

• Build an opinion supernetwork model with four subnetworks

• Explore opinion dynamics based on the opinion supernetwork model

• Put forward superedge prediction algorithm

• Give a case study to calculate prediction results and analyze dynamic processes

摘要

How do Internet users' opinions evolve under the influence of factors such as information environment and psychological forces? We developed an opinion supernetwork model with social, environmental, psychological and keyword subnetworks. This model integrated a combination of external and internal factors which influence opinion formation. From a different perspective, we applied superedge prediction, which is a novel link prediction method based on the supernetwork model, to analyze emerging superedges in the opinion supernetwork model. Comparing the predicted network with actual network, we revealed a fair amount of consistency between them. In addition, based on the predicted opinion supernetwork model, we investigated opinion dynamics, which shed some light on public opinion governance.

论文关键词:Public opinion,Supernetwork,Superedge prediction

论文评审过程:Received 18 April 2013, Revised 2 April 2014, Accepted 8 May 2014, Available online 20 May 2014.

论文官网地址:https://doi.org/10.1016/j.dss.2014.05.011