Because of its widespread user base and instantaneous, ever-flowing design, we often hear about breaking news on Twitter before we hear it from actual news outlets. The US Geological Survey has decided to capitalize on this, and is now using Twitter to track earthquakes.
The USGS National Earthquake Information Center only has 2,000 earthquake sensors, and most of them are in the US. This leaves the USGS without access to earthquake data for large portions of the planet, so the agency has started culling data from Twitter users.
On Twitter's official blog, communications manager Elaine Ellis describes in detail how the USGS filtered the vast number of tweets being posted to find the ones that were the most relevant.
They found that people Tweeting about actual earthquakes kept their Tweets really short, even just to ask, "earthquake?" Concluding that people who are experiencing earthquakes aren't very chatty, they started filtering out Tweets with more than seven words. They also recognized that people sharing links or the size of the earthquake were significantly less likely to be offering firsthand reports, so they filtered out any Tweets sharing a link or a number. Ultimately, this filtered stream proved to be very significant at determining when earthquakes occurred globally.
For example: when an earthquake began in Colorado, the USGS received an email alert about an aftershock in Chile in less than two minutes, triggered by 14 tweets from their specially-filtered feed.
This just serves as a reminder that somewhere amongst all the memes, trolls, and spambots, there are real people adding potentially useful data to the collective consciousness. Kudos to the USGS for finding a way to harness that data.