Interest aware seed node detection for information diffusion in online social networks

Information dissemination in Online Social Networks (OSNs) is shaped both by the structural foundation of the network and by the interest-based relationships among its users. Identifying the seed users of information diffusion in OSNs remains a challenge. Traditional seed detection methods apply centrality measures globally to uncover seed nodes and overlook seed detection based on interest groups. As a result, the selected seed nodes are often concentrated in the same locality, and efficient information diffusion remains a challenge. In this paper, we propose an interest group-based seed node detection framework for information dissemination in OSNs. The proposed approach first finds the interest groups using the Leiden community detection method; once all interest groups are detected, the seed nodes within each group are identified using Netdegree Centrality (NDC), a variant of degree centrality. Selecting influential seed nodes from every interest group ensures diversified and efficient information diffusion over the network. Experimental evaluation on eight benchmark datasets using the Independent Cascade (IC) model of information diffusion shows that the seeds selected across the different interest groups achieve good diffusion coverage of the whole network. The results show that the proposed approach combines community-aware analysis with local influence metrics for seed detection in varied and scalable OSNs.