Dynamic Network Modeling of Workplace Titles in the Big Data Environment: A Study Based on GNN Model

In the era of big data, the use and change of workplace titles not only reflect hierarchies and relationships within an organization, but also have a significant impact on employees' job satisfaction and performance. However, most current research on workplace titles focuses on static network analysis and lacks exploration of dynamic network modeling. In order to address this problem, this project proposes to use a Graph Neural Network (GNN) based approach to model the dynamic network of employee address behavior. On this basis, our proposed GCN-based algorithm can effectively improve the learning efficiency of the neural network, in which the prediction accuracy increases from 0.62 to 0.87 with the increase of the number of model layers, while the training time increases from 8.34 to 53.12 seconds. By analyzing the results of these experiments, we can see the important role of the GNN method for dynamic modeling of workplace workplace title relationships.