Discover Tipping Users For Cross Network Influencing

Traditional viral marketing problem aims at selecting a set of influential seed users to maximize the awareness of products and ideas in one single social network. However, in real scenarios, users' profiles in the target social network (e.g., Facebook) are usually confidential to the public, which block the conventional viral marketing strategies reaching the target consumers effectively. Instead, since users nowadays are usually involved in multiple social networks simultaneously, the viral marketing can actually be performed in other public networks. These networks with public profile information are referred as the source networks, from which information can diffuse to and activate users in the target network indirectly. Thus in the cross-network information diffusion, besides the influential seed users, those who act as bridges propagating information between networks actually play a more important role and some can trigger the tipping point in the target network, who are named as the tipping users formally. Motivated by this, in this paper, we studied the "Discovering Tipping Users for Cross Network Influencing" (TURN) problem across multiple aligned heterogeneous social networks. To depict the information diffusion process across aligned heterogeneous social networks, we propose a novel network information diffusion model, "Cross Network Information Diffusion" (CONFORM). In CONFORM, various diffusion links in the heterogeneous networks are extracted and fused by weight to calculate the users' activation probabilities. To address the TURN problem, a new method called "Tipping Users Discovery Algorithm (TUDOR)" is proposed to identify the tipping users who bring about the largest influence gain, which is a new concept first introduced in this paper. Extensive experiments are conducted on real-world social network datasets, which demonstrate the effectiveness and efficiency of TUDOR.