Maximizing Information Dissemination in Social Network via a Fast Local Search

In recent years, social networks have become increasingly popular as platforms for personal expression, commercial transactions, and government management. The way information propagates on these networks influences the quality and expenses of social network activities, garnering substantial interest. This study addresses the enhancement of information spread in large-scale social networks constrained by resources, by framing the issue as a unique weighted k-vertex cover problem. To tackle this complex NP-hard optimization problem, a rapid local search algorithm named FastIM is introduced. A fast constructive heuristic is initially used to quickly find a starting solution, while a sampling selection method is incorporated to minimize complexity during the local search. When the algorithm stalls in local optima, a random walk operator reorients the search towards unexplored regions. Comparative tests highlight the proposed method's robustness, scalability, and efficacy in maximizing information distribution across social networks. Moreover, strategy validation trials confirm that each element of the framework enhances its overall performance.