Model-Based Learning of Information Diffusion in Social Networks

In recent years, the ability to predict how information will travel within a network has gained importance, especially in the setting of online social media platforms where the dissemination of information can have a big impact on social and political events. Researchers frequently employ a range of methods, such as network mapping and analysis, data mining, and machine learning algorithms, to study social networks and the connections between them. These methods can be used to locate important nodes and influential nodes within a network and to comprehend the underlying dynamics that govern the dissemination of knowledge. This research work attempts to study the use of three different epidemic models to a medium level twitter network of size 35,000 nodes. This paper discusses the impact of centrality measures, the use of hyperparameters and the results of models in detail. It recommends the suitable social network epidemic model for better information diffusion in the network, which can be adopted by businesses for digital marketing or advertising.