DySuse: Susceptibility Estimation in Dynamic Social Networks

As a fundamental task in the field of social Influence estimation has been studied along with influence computing, influence estimation focuses on mining such maximization for years, and most work estimates the complex and rich information from the macro perspective influence by repetitively simulating the influence diffusion to support many social applications such as viral marketing process. To simulate the influence diffusion process, Independent (Zhou et al., 2019a), social recommendation (Chen and Cascade (IC) diffusion model and Linear Threshold Wong, 2021), etc. Given a social network and an initial set of (LT) diffusion model have been proposed by Kempe et seed users, traditional influence estimation (Wu and Wang, al. (Kempe et al., 2003). As two simple but fundamental 2020) aims at predicting how many users are influenced by diffusion models, the IC model assumes that a user may the initial set of seed users (i.e., influence spread), while be influenced by one of its neighbors, and each influenced neglects individual susceptibility. Susceptibility estimation user has a certain probability of influencing its neighbors. In focuses on predicting the probability of an individual user contrast, in the LT model, a user will be influenced once the being influenced from the microscopic perspective and has total influence of all its neighbors exceeds a threshold. Based extensive applications in practice. For instance, in marketing on these two diffusion models, Kempe et al. (Kempe et al., activities, enterprises can use susceptibility estimation to 2003) generalize them to a model called the triggering (TR) identify the potential users who are most likely to purchase diffusion model.