Member company, SAM rolled out v2 of its product in beta a few weeks ago. After years of serving newsrooms with tools for social media workflow and verification, the team has collected an incredible wealth of knowledge on valuable real-time data. UGC (user generated content) has potential to transform so many industries, allowing people to better understand the world around them, make better business decisions, keep people safe, and tell stories that matter. The team at SAM is committed to building tools that help their customers leverage the incredible power of millions of real-time data points.
In this product update, Sean Solbak, CTO, shares insight into how their new knowledge engine can alert to natural disaster faster than government and news sources. SAM cuts through the clutter using proprietary AI algorithms that scan social media, understand what's being said, where it's being said, and, critically, the authenticity of who is saying it.
Read on for examples of SAM v2 in action.
Using Our Real-Time Knowledge Engine to Alert on Earthquakes Faster Than Government Sources
Two weeks ago, we unveiled the public beta of our real-time knowledge engine. Here is one example of how we help our users know what is happening when it happens.
At 14:03 GMT, on Saturday, Feb. 17th, a 4.6 magnitude earthquake was registered 20 km northeast of Swansea, Wales, UK. The first public acknowledgement of the earthquake came from the British Geological Survey (BGS) 50 minutes later, stating they were analyzing the data. 1 hour and 13 minutes after the quake, BGS announced that Swansea was the nearest and hardest hit.
While SAM does pull in critical official reports, our system is not solely reliant on government data or media channels. SAM’s AI scans social chatter from on-the-ground sources to detect anomalies and triangulate where these events are happening. Our real-time knowledge engine detected the first Swansea earthquake report at 14:33 GMT and alerted our users at 14:35 GMT. This gave our users an 18-minute head start over the first BGS alert and a 39-minute head start compared to the first BBC Breaking alert.