Influence maximization algorithm based on reducing search space in the social networks

The influence maximization problem in social networks is an optimization problem in viral marketing. This problem is concerned with identifying a certain number of people with the most influence in the social network level. Considering the NP-hard of this problem, finding an optimal solution with acceptable accuracy and the low running time is of the high importance. To this purpose, GIN (Group of Influential Nodes) algorithm is presented in this article which creates different groups of graph nodes with more connections than other groups. Then, it selects specific nodes from each group to reduce the search space to find the most influential nodes. Following the greedy method, it selects the seed nodes with the highest expected diffusion value. Experimental results show that the GIN algorithm has provided high influence spread along with low running time in comparison algorithms on all seven real-world datasets.