DNA-inspired online behavioral modeling and its application to spambot detection

Research on online behavioral modeling often focuses on social media users. We propose a strikingly novel, simple and effective approach to support this research methodology: we model user behavior by extracting digital DNA sequences from their online collected actions and we use Twitter as a benchmark to test our proposal. In particular, we firstly show how to obtain a compact and effective DNA-inspired characterization of user actions. 

Then, we suggest specific applications of our methodology. As a case study, we apply standard DNA analysis techniques in order to discriminate between genuine and spambot accounts on Twitter, further supporting our solution by an experimental campaign. To the best of our knowledge, we are the first ones to identify and adapt DNA-inspired techniques to online user analysis. 

While Twitter spambot detection is a specific use case on a specific social media, our proposed methodology is platform and technology agnostic, hence paving the way for diverse behavioral characterization tasks.