Dai Caiyan, Chen Ling, Hu Kongfa, Ding Youwei
College of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing 210023, China.
College of Information Engineering, Yangzhou University, Yangzhou 225012, China.
Entropy (Basel). 2022 Nov 8;24(11):1623. doi: 10.3390/e24111623.
This paper presents a method to minimize the spread of negative influence on social networks by contact blocking. First, based on the infection-spreading process of COVID-19, the traditional susceptible, infectious, and recovered (SIR) propagation model is extended to the susceptible, non-symptomatic, infectious, and recovered (SNIR) model. Based on this model, we present a method to estimate the number of individuals infected by a virus at any given time. By calculating the reduction in the number of infected individuals after blocking contacts, the method selects the set of contacts to be blocked that can maximally reduce the affected range. The selection of contacts to be blocked is repeated until the number of isolated contacts that need to be blocked is reached or all infection sources are blocked. The experimental results on three real datasets and three synthetic datasets show that the algorithm obtains contact blockings that can achieve a larger reduction in the range of infection than other similar algorithms. This shows that the presented SNIR propagation model can more precisely reflect the diffusion and infection process of viruses in social networks, and can efficiently block virus infections.
本文提出了一种通过阻断接触来最小化社交网络中负面影响传播的方法。首先，基于COVID-19的感染传播过程，将传统的易感、感染和康复（SIR）传播模型扩展为易感、无症状、感染和康复（SNIR）模型。基于该模型，我们提出了一种估计在任何给定时间被病毒感染的个体数量的方法。通过计算阻断接触后感染个体数量的减少，该方法选择能够最大程度减少受影响范围的要阻断的接触集。重复选择要阻断的接触，直到达到需要阻断的孤立接触数量或所有感染源被阻断。在三个真实数据集和三个合成数据集上的实验结果表明，该算法获得的接触阻断能够比其他类似算法在感染范围上实现更大的减少。这表明所提出的SNIR传播模型能够更精确地反映病毒在社交网络中的扩散和感染过程，并且能够有效地阻断病毒感染。
