A memetic algorithm for maximizing earned attention in social media

Abstract

With the advent of social media in our lives and the transformation of consumer behaviour through the impact of Internet Technology, online brand-human interactions are crucial in the consumer decision-making process, as well as on corporate performance. This study develops a model to predict behavioural brand engagement as measured in terms of the amount of consumer’s earned attention. The exogenous variables adopted in the model comprise longitudinal behavioural parameters related to online traffic, flow of consumer-initiated brand commentaries and the quantity of brand mentions. To test and validate the research model, we apply a Memetic Algorithm (MA) which is well tailored to the phenomenon of propagation and social contagion. This evolutionary algorithm is assessed through the comparison with a standard alternative procedure – the Steepest Ascent (SA) heuristic. Results show that the shape of the utility functions considered in the model has a huge impact on the characteristics of the best strategies, with actions focused on increasing a single variable being preferred in case of constant marginal utility, and more balanced strategies having a better performance in the case of decreasing marginal utility. Insights and implications for research and practice are then provided.