When you tweet ‘earthquake,’ you’re helping the USGS track seismic events

California, like many areas around the world, is prone to earthquakes. And when one strikes, people are prone to tweet about it (c’mon, admit it). But did you know that your tweet is being used by the U.S. Geological Survey to help track these events?

In its latest #DataStories, Twitter revealed that during the Sichuan earthquake in 2008, Twitter was faster at reporting the earthquake than USGS was. And it’s no wonder either, as the USGS has only 2,000 real-time earthquake sensors around the world, with most located in the U.S. So the agency turned to Twitter and its 316 million monthly active users to help keep them informed.

But it wasn’t without reservations:

At first, the USGS staff was a bit skeptical that Twitter could be used as a detection system for earthquakes — but when they looked into it, they were surprised at the effectiveness of Twitter data for detection.

The USGS taps into Twitter’s Public API to look at your tweets and creates a baseline for earthquake-related chatter using its time series event detection method. Only short tweets (you know, the ones where all you ask is “earthquake?”) and those without a link or number are analyzed.

Twitter’s communications manager Elaine Ellis wrote that on any given day, the USGS’s National Earthquake Information Center processes about 70 earthquakes, with only a “small handful” being felt by people because some take place in the ocean, deep in the earth, or where no one is really around:

Twitter data can be crucial in helping identify earthquakes felt by humans, and can trigger an alert typically in under two minutes. The 2014 earthquake in Napa was detected by USGS in 29 seconds using Twitter data, likely due to the tech savvy population that dominates the area. (Origin time was 2014-08-24 10:20:44 UTC and Twitter data detection time was 2014/08/24 10:21:13.)

And it’s not just the word “earthquake” that USGS looks at, but also the different translations.

In the future, the agency hopes to turn Twitter-data-based detection into seismic algorithms to accelerate alerts further.