Modeling Influencer Marketing Campaigns in Social Networks

TL;DR

The paper introduces a probabilistic, graph-based ABM to simulate influencer marketing campaigns on social networks, incorporating product type, consumer interest, willingness to pay, engagement, and network structure. Using BFS-like propagation with depth attenuation, the model compares celebrities, mega-, macro-, and nano-influencers under diverse scenarios and budgets. Key findings show that the best influencer strategy is highly contingent on product luxury and initial audience interest, with nano-influencers outperforming celebrities for non-luxury products at high interest, while celebrities can be preferable for certain luxury cases; CAC and conversion often diverge, underscoring trade-offs in campaign planning. The framework supports scenario analysis for campaign design and can be extended to study misinformation spread and other network phenomena.

Abstract

Social media are extensively used in today's world, and facilitate quick and easy sharing of information, which makes them a good way to advertise products. Influencers of a social media network, owing to their massive popularity, provide a huge potential customer base. However, it is not straightforward to decide which influencers should be selected for an advertizing campaign that can generate high returns with low investment. In this work, we present an agent-based model (ABM) that can simulate the dynamics of influencer advertizing campaigns in a variety of scenarios and can help to discover the best influencer marketing strategy. Our system is a probabilistic graph-based model that provides the additional advantage to incorporate real-world factors such as customers' interest in a product, customer behavior, the willingness to pay, a brand's investment cap, influencers' engagement with influence diffusion, and the nature of the product being advertized viz. luxury and non-luxury. Using customer acquisition cost and conversion ratio as a unit economic, we evaluate the performance of different kinds of influencers under a variety of circumstances that are simulated by varying the nature of the product and the customers' interest. Our results exemplify the circumstance-dependent nature of influencer marketing and provide insight into which kinds of influencers would be a better strategy under respective circumstances. For instance, we show that as the nature of the product varies from luxury to non-luxury, the performance of celebrities declines whereas the performance of nano-influencers improves. In terms of the customers' interest, we find that the performance of nano-influencers declines with the decrease in customers' interest whereas the performance of celebrities improves.

Figures (9)

• Figure 1: Out-degree distribution of the datasets
• Figure 2: Validation of individual and set performance of the influencers
• Figure 3: Simulation results for a non-luxury product with respect to different types of influencer sets, and their corresponding size $n$. The horizontal axis represents categorical data. The customer acquisition cost is found to decrease when using smaller types of influencers whereas the conversion ratio increases.
• Figure 4: Simulation results for a luxury product with respect to different types of influencer sets, and their corresponding size $n$. The horizontal axis represents categorical data. (a) The customer acquisition cost is found to increase when using smaller types of influencers whereas the conversion ratio decreases. (b) When the customers' interest in the product is already high, both the customer acquisition cost and the conversion ratio decrease when using smaller types of influencers.
• Figure 5: Results of the parametric sweep for the Twitter graph represented as a contour map: the dashed line represents the boundary between celebrities (in blue) or nano-influencers (in red) being the better performers. The gradient represents the magnitude of their difference.