Multi-criteria approach to viral marketing campaign planning in social networks, based on real networks, network samples and synthetic networks

Abstract

Spreading of information within social media and techniques related to viral marketing take more and more attention from companies focused on targeting audiences within electronic systems. Recent years resulted in extensive research centered around spreading models, selection of initial nodes within networks and identification of campaign characteristics affecting the assumed goals. While social networks are usually based on complex structures and high number of users, the ability to perform detailed analysis of mechanics behind the spreading processes is very limited. The presented study shows an approach for selection of campaign parameters with the use of network samples and theoretical models. Instead of processing simulations on large network, smaller samples and theoretical networks are used. Results showed that knowledge derived from relatively smaller structures is helpful for initialization of spreading processes within the target network of larger size. Apart from agent based modeling, multi-criteria methods were used for evaluation of results from the perspective of costs and performance.