The growth and worldwide success of Twitter has surfaced natural limitations of hashtags and keyword searches. What was once a mechanism for organizing information for efficient consumption has been made impractical by overwhelming volume and diversity of discussion. Word embedding technology promises to change real-time analytics as much as it has effected static data analytics by making it possibly to follow events as they change in real time. But what does that mean, and what does big text look like? We’ll explore how using this new type of machine learning on streaming data allows for an evolving look at unfolding events with case studies of the ISIS “topic of the moment” and fear around the Zika virus outbreak. Beyond that, we’ll touch on the challenges of running text analytics for the 2014 World Cup (the biggest social media event yet) and discuss lessons learned and techniques used in order to cover the games in real time.