Maximizing Social Influence With Minimum Information Alteration

With the rapid advancement of the Internet and social platforms, how to maximize the influence across popular online social networks has attracted great attention from both researchers and practitioners. Almost all the existing influence diffusion models assume that influence remains constant in the process of information spreading. However, in the real world, people tend to alternate information by attaching opinions or modifying the contents before spreading it. Namely, the meaning and idea of a message normally mutate in the process of influence diffusion. In this paper, we investigate how to maximize the influence in online social platforms with a key consideration of suppressing the information alteration in the diffusion cascading process. We leverage deep learning models and knowledge graphs to present users' personalised behaviours, i.e., actions after receiving a message. Furthermore, we investigate the information alteration in the process of influence diffusion. A novel seed selection algorithm is proposed to maximize the social influence without causing significant information alteration. Experimental results explicitly show the rationale of the proposed user behaviours deep learning model architecture and demonstrate the novel seeding algorithm's outstanding performance in both maximizing influence and retaining the influence originality.