Multiple Q-DQN Algorithm based Rumor Control in Social Networks

Malicious rumours on social media platforms like Facebook, Twitter, and others can be widely disseminated because of social problems. It is challenging to manage a rumour once it gains growth and quickly moves throughout a network. One of the main issues with information dissemination is figuring out how to reduce the propagation of rumours within a social network. A deep reinforcement learning technique might be an effective strategy to manage the rumour issue. Deep Q learning network (DQN) has been used in the literature to mitigate rumors by selecting a blocker at each time step. In this work, the proposed Multiple-Q-DQN is introduced as a stepwise discrete-time optimization method for rumor control to address the rumor influence minimization problem. The Multiple-Q-DQN model helps identify and select two blocker nodes at each time step while considering the changing state of the network. This implies that rather than using a static technique that is ineffective in light of changes, the strategy might take into account the network's present status. Additionally, sequential decision-making—a methodical optimisation process—is employed. The infection rate and comparisons with baseline and competitive methods are used to analyse the model's performance using four real-world datasets, including American football, Facebook, Zachary Karate Club, and Dolphins. The Multiple-Q-DQN is superior to the baseline in terms of infection rate at the first time step on the Facebook network (0.09:0.10), Karate network (0.03:0.07), and Dolphins network (0.02:0.09), except for the Football network (0.09:0.09). Also, all networks are superior to all related works, while the Facebook network is competitive with related works.