Threat Evaluation Method of Social Network Nodes Based on PSO
Xiujuan Wang, Siwei Cao, Haoyang Tang, Yutong Sh, Yi Sui · 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · 2021
This paper proposes a method for evaluating the threat of social network nodes based on Particle Swarm optimization (PSO), including in the assessment of node anomaly degree and node influence, the assessment of node influence pays more attention to the ability of nodes to disseminate information on social platforms, and the PSO is selected to determine the parameters involved in the calculation. Finally, combined with the calculated node anomaly score, the final node threat degree is obtained. Experimental results show that the method proposed in this study can increase the spearman rank correlation coefficient between the expected value of tweets to be reposted calculated in the previous study and the actual reposting situation from the original highest 0.5599 to 0.6129. Comparing the results calculated by this method with the results of the PageRank algorithm, the reliability of the method is verified.