LAUSR

In this paper, we explore a real-time automation challenge: the problem of focused extraction of Social Media users. This challenge can be seen as a special form of focused crawling where the main target is to detect users with certain patterns. Given a specific user profile, the task consists of rapidly ingesting Social Media data and early detecting target users. This is a real-time intelligent automation task that has numerous applications in domains such as safety, health or marketing. The volume and dynamics of Social Media contents demand efficient real-time solutions able to predict which users are worth to explore. To meet this aim, we propose and evaluate several methods that effectively allow us to harvest relevant users. Even with little contextual information (e.g., a single user submission), our methods quickly focus on the most promising users. We also developed a distributed microservice architecture that supports real-time parallel extraction of Social Media users. This modular architecture scales up in clusters of computers and it can be easily adapted for user extraction in multiple domains and Social Media sources. Our experiments suggest that some of the proposed prioritisation methods, which work with minimal user context, are effective at rapidly focusing on the most relevant users. These methods perform satisfactorily with huge volumes of users and interactions and lead to harvest ratios 2 to 9 times higher than those achieved by random prioritisation.