Using principal eigenvectors of Laplacian-Plus matrix to identify spreaders of social networks under linear threshold diffusion model

Influence maximization (IM) is a challenging problem in social networks to identify initial spreaders with the best influence on other nodes. It is a need to solve this problem with the minimum diffusion time and the most coverage on the communities. However, the spreaders are rarely dependent on diffusion models. A recent research [N. Binesh, M. Ghatee, Distance-Aware Optimization Model for Influential Nodes Identification in Social Networks with Independent Cascade Diffusion, Information Sciences, 581 (2021) 88-105] proposed DASF algorithm for spreaders selection by the Independent Cascade (IC) diffusion model. Here, we present a new optimization model to find spreaders under Linear Threshold (LT) diffusion model. LT is one of the most important models to imitate the behavior of influence propagation in social networks. Our model is a quadratic programming problem based on Laplacian-Plus matrix. We derive its solution by some principal eigenvectors of Laplacian-Plus matrix. We organize the solution process as DALT algorithm. Without community detection, it can identify the spreaders with maximum inter-communities distance, minimum intra-communities distance, and the most significant degrees. By considering various well-known social networks, we show that DALT provides brilliant results and overcomes other local and global spreader finders, especially in social networks with community structures.