Community based acceptance probability maximization for target users on social networks: Algorithms and analysis

Abstract Different from previous social influence problems such as Influence Maximization (IM), we in this paper first propose the Acceptance Probability Maximization (APM) problem, i.e., we select a seed set S with a budget b such that the acceptance probability of the target user set T is maximized. Then we employ the classical Independent Cascade (IC) model as the information diffusion model. Based on the IC model, we prove that the APM problem is NP-hard and the objective function is monotone non-decreasing and submodular. Considering community components of the social network, we convert the APM problem to the Maximum Weight Hitting Set (MWHS) problem. Next we develop a pipage rounding algorithm whose approximation ratio is ( 1 − 1 / e ) . Furthermore, we also propose a basic greedy algorithm and a heuristic algorithm as comparison methods. Finally, we conduct extensive simulations on synthetic and real-life social networks to evaluate the efficacy and efficiency of our algorithms. Empirical evaluation results validate the superiority of proposed algorithms in both effectiveness and efficiency compared with a few baseline comparison methods.