Identifying effective nodes in term of the influence maximization on the social IoT networks using deep learning-based node embedding

The advent of the Internet of Things (IoT) has ushered in an era of unprecedented connectivity, transforming the way we interact with the world around us. As technology continues to advance, the concept of the Social Internet of Things (SIoT) has emerged, adding a human-centric dimension to the interconnectivity of devices. Identifying effective nodes in influence maximization is one of the most key issues in the challenges of SIOT networks. In this paper, a novel method is proposed to identify effective nodes in influence maximization in the SIOT network. In the proposed method, the EITM framework is proposed, in which effective nodes are identified by combining network embedding and deep learning. In the deep learning process, an LSTM network is designed to predict effective nodes in influence maximization. The results show that the EITM method performed better than other conventional methods in identifying effective nodes in influence maximization. Also, the results show that the EITM method is a decentralized method that increases the possibility of maximizing influence compared to centralized methods. Finally, the results show that mobile devices play a more important role in influence maximization than static devices.