Perceived Popularity Maximization in Social Networks

In this paper, we provide a method for maximizing consumers’ collective perception of the popularity of a brand by leveraging social network structure. A stream of research on the majority illusion has shown that people can collectively overestimate the popularity of an attribute depending on the network positions of individuals possessing that attribute. Another stream of research in marketing shows the benefits conferred to brands that are perceived as popular. These two streams of research suggest that (1) it is in a marketer’s best interest to maximize the collective perception of their brand’s popularity, and (2) this can be achieved by encouraging brand adoption in individuals who are properly positioned within the network structure. Which consumers, then, are the ones who are best positioned to maximize the collective perception of the brand’s popularity? To what extent should each of these consumers be encouraged to adopt the brand via advertising? We frame these questions as a budget allocation problem, which we call perceived popularity maximization. We show that this problem is a special case of a more general combinatorial optimization problem that may be solved approximately using a simple greedy algorithm. We present the results of tests of this greedy algorithm on real social network data and find that consumers can be induced to overestimate a brand’s popularity by several times by properly allocating the advertising budget.