دانلود رایگان مقاله انگلیسی به حداکثر رساندن نفوذ در شبکه های اجتماعی برای بازاریابی ویروسی - اشپرینگر 2018

Abstract

Modeling influence diffusion in social networks is an important challenge. We investigate influence-diffusion modeling and maximization in the setting of viral marketing, in which a node’s influence is measured by the number of nodes it can activate to adopt a new technology or purchase a new product. One of the fundamental problems in viral marketing is to find a small set of initial adopters who can trigger the most further adoptions through word-of-mouth-based influence propagation in the network. We propose a novel multiple-path asynchronous threshold (MAT) model, in which we quantify influence and track its diffusion and aggregation. Our MAT model captures not only direct influence from neighboring influencers but also indirect influence passed along by messengers. Moreover, our MAT framework models influence attenuation along diffusion paths, temporal influence decay, and individual diffusion dynamics. Our work is an important step toward a more realistic diffusion model. Further, we develop an effective and efficient heuristic to tackle the influence-maximization problem. Our experiments on four real-life networks demonstrate its excellent performance in terms of both influence spread and time efficiency. Our work provides preliminary but significant insights and implications for diffusion research and marketing practice.

Conclusion

In this paper, we propose a novel multiple-path asynchronous threshold (MAT) model for viral marketing in social networks. It differs from existing diffusion models in several aspects. We quantitatively measure influence and keep track of its spread and aggregation during the diffusion process. Our MAT model captures both direct and indirect influence, depth-associated influence attenuation, temporal influence decay, and individual diffusion dynamics. Our work is an important step toward a more realistic diffusion model. Further, we develop an effective and efficient heuristic, IV-Greedy, to tackle the influencemaximization problem. Our experiments on four real-life networks demonstrate its excellent performance in terms of both influence spread and time efficiency. Our work provides preliminary but significant insights and implications for marketing practice. Firs of all, unlike other diffusion models relying exclusively on the direct influence from influencers, our model draw managerial attention to messengers who play an important role in spreading indirect influence in viral marketing. Our model offers an algorithmic view of the complex WOM communications, as described in the network coproduction model (Kozinets et al. 2010). Second, our work provides pragmatic implications for how marketers should plan and leverage WOM campaigns. They need to take into consideration depth-associated influence attenuation and temporal influence decay when determining the time period/steps. Specifically, it is necessary for the marketers to find out the decay rate attuned to the product and/or social media of interest. Third, to fully grasp the effect of the WOM marketing, marketers need to look beyond the network structure and incorporate the weight information on edges to capture the network activeness and individual diffusion dynamics. Finally, our work suggests that marketers can create an efficient seeding strategy that achieves larger influence spread than the high-degree seeding. They need to consider both individual influence spread and the network structure to minimize the potential overlaps.