Social Media Can Help Track Tornadoes, But Was That Tweet Real? : All Tech Considered Researchers at Purdue are using software to mine tweets for data that can help warn that a dangerous storm is approaching. But the data may not always be reliable and analyzing it can be tricky.
NPR logo

Social Media Can Help Track Tornadoes, But Was That Tweet Real?

  • Download
  • <iframe src="https://www.npr.org/player/embed/400125638/400929940" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript
Social Media Can Help Track Tornadoes, But Was That Tweet Real?

Social Media Can Help Track Tornadoes, But Was That Tweet Real?

  • Download
  • <iframe src="https://www.npr.org/player/embed/400125638/400929940" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript

STEVE INSKEEP, HOST:

When I was in junior high school in Indiana, I had a classmate in the weather business. He gathered climate information and sent it to the National Weather Service. Today, thanks to social media, almost anybody on the planet could send on information, and it could save lives during a tornado. There is of course one problem, my friend a junior high school actually knew what he was talking about. The National Weather Service and Purdue University researchers want to know what they can really learn from social media. Here's Stan Jastrzebski of member station WBAA.

STAN JASTRZEBSKI, BYLINE: As the big storm bore down on Rockford, Ill., students in a Purdue classroom prepare the track its effects using Twitter. Using software jointly developed by Purdue, the Department of Homeland Security and the National Weather Service, students huddle around laptops to analyze a tiny sample of the tweets from the storm's immediate vicinity. They're looking for keywords like damage or tornado and for pictures of funnel clouds. Their professor, Tim Filley, says social media can track a storm's path of destruction just as radar does.

TIM FILLEY: You can overlay storm tracks and the people who have been responding to the storm. It actually maps out very nicely when people are talking about damage.

JASTRZEBSKI: A couple days later, software developer Jiawei Zhang pulls up a map showing blue-green blobs near Rockford and in eastern Iowa, indicating there had been lots of tweets there. He found them by searching for keywords related to safety, security and severe weather. One Iowa tweet he clicks on from a person apparently in the path of a tornado sounds heartbreaking.

JIAWEI ZHANG: This tweet talks about the storm killed my family. I'm the only one left in my basement.

JASTRZEBSKI: The problem is there's no evidence that actually happened. No one in Iowa died in the storm.

KAETHE BECK: And so I don't think you could go with just critical mass - right? - because just because Kim Kardashian says something's true doesn't make it true.

JASTRZEBSKI: Kaethe Beck is coordinating the research for this effort. She's trying to determine just whom to trust on Twitter.

BECK: One of the other research components is, are these reliable sources? So if somebody tweets, I just saw the barn ripped apart, or, you know, there's an accident on this highway, or somebody just walked in here with a weapon, is that a reliable source? How can we trust that?

JASTRZEBSKI: Beck says the program contains an algorithm that attempts to weed out bad information by looking at how often a Twitter user's messages are retweeted and by trying to determine if that person has been factual in the past. But there's another problem - Twitter's audience skews younger, more urban and more well-to-do than the population as a whole. So the elderly farmer in northern Illinois who might have been in the way of last week's storm is less likely to see tweets telling him of the danger. That's a quandary Tim Filley and his students are trying to solve.

FILLEY: And so that's actually part of the discussion. You know, are we biasing our information, biasing our story based upon granularity of data and age bias?

JASTRZEBSKI: The National Weather Service wants to improve its social media presence using this sort of data mining, but the data need to be factual. Even when they are, meteorologist Jason Puma says there can be a disconnect between someone retweeting hash tag #takecover and actually acting on that message.

JASON PUMA: For most people, they don't take action until they personally recognize some sort of threat to themselves.

JASTRZEBSKI: Beck says her analysis confirms people don't always act smartly in the face of a storm.

BECK: I just think it's interesting, you know, people taking photos instead of taking cover.

JASTRZEBSKI: Though the tracking programs is always running, it's still better at after-the-fact analysis than it is at real-time warning. As it improves, first responders could conceivably target areas most in need of help based on the tweet content. Those in the way of the storm would get a few extra seconds to reach their storm cellars which could save lives. For NPR News, I'm Stan Jastrzebski in West Lafayette, Ind.

INSKEEP: He's with WBAA which operates under a license held by Purdue, though the newsroom operates independently. It's MORNING EDITION from NPR News. I'm Steve Inskeep.

RENEE MONTAGNE, HOST:

And I'm Renee Montagne.

Copyright © 2015 NPR. All rights reserved. Visit our website terms of use and permissions pages at www.npr.org for further information.

NPR transcripts are created on a rush deadline by Verb8tm, Inc., an NPR contractor, and produced using a proprietary transcription process developed with NPR. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR’s programming is the audio record.