۱- Introduction

۲- State of the art in viral marketing

۳- The agent-based market simulation model

۴- Multiobjective viral marketing optimization problem

۵- Evolutionary multiobjective optimization methods for influentials selection

۶- Experiments and analysis of results

۷- Main conclusions and limitations of the study

References

Abstract

Marketers have an important asset if they effectively target social networks’ influentials. They can advertise products or services with free items or discounts to spread positive opinions to other consumers (i.e., word-of-mouth). However, main research on choosing the best influentials to target is single-objective and mainly focused on maximizing sales revenue. In this paper we propose a multiobjective approach to the influence maximization problem with the aim of increasing the revenue of viral marketing campaigns while reducing the costs. By using local social network metrics to locate influentials, we apply two evolutionary multiobjective optimization algorithms, NSGA-II and MOEA/D, a multiobjective adaptation of a single-objective genetic algorithm, and a greedy algorithm. Our proposal uses a realistic agent-based market framework to evaluate the fitness of the chromosomes by simulating the viral campaigns. The framework also generates, in a single run, a set of non-dominated solutions that allows marketers to consider multiple targeting options . The algorithms are evaluated on five network topologies and a real data-generated social network, showing that both MOEA/D and NSGA-II outperform the single-objective and the greedy approaches. More interestingly, we show a clear correlation between the algorithms’ performance and the diffusion features of the social networks.

Introduction

On-line social networks such as Facebook or Instagram make people (potential consumers) more connected than ever before. With just a few actions, consumers can instantly communicate their products and brands’ opinions. Social networks’ influentials have thousands of friends and a wordof-mouth process can create a cascade of positive or negative information about a brand. This word-of-mouth process in social networks is crucial for marketers and advertisers (Leskovec et al., 2007; Haenlein and Libai, 2017). In fact, people place more value in friends’ recommendations than in those from traditional advertisement channels such as TV. Viral marketing (VM) consists of targeting certain consumers to encourage a faster product’s adoption (Haenlein and Libai, 2017). The selection of these influentials is not a random but a complex optimization process that involves the analysis of the social network of consumers to trigger a large cascade of adoptions (known in the literature as influence maximization (IM) (Domingos and Richardson, 2001)) thus favoring a positive information diffusion. Designing the best VM strategies before running them in the real market is possible through the use of artificial social networks (Watts and Dodds, 2007) and simulations using paradigms such as agent-based modeling (ABM) (Epstein, 2006). ABM can describe and simulate networklevel interactions between consumers to reproduce word-of-mouth mechanisms that provide realism into marketing models and allow modelers to study emergent behaviors (Janssen and Jager, 2003; Epstein, 2006). These models enable the aggregation of individual-level interactions through the underlying artificial social network, creating high level outcomes and incorporating individual behavioral rules without higher level assumptions (Chica et al., 2018).