Influencer Detection with Dynamic Graph Neural Networks

Leveraging network information for prediction tasks has become a common practice in many domains. Being an important part of targeted marketing, influencer detection can potentially benefit from incorporating dynamic network representation. In this work, we contribute to the literature by investigating different dynamic Graph Neural Networks (GNNs) configurations for influencer detection and evaluate their prediction performance using a unique corporate data set. We show that encoding temporal attributes and having a history of node dynamics prior to making predictions significantly impact performance. Furthermore, our empirical evaluation illustrates that network centrality measures are more beneficial than capturing neighborhood representation.