It looks like you're using an Ad Blocker.

Please white-list or disable in your ad-blocking tool.

Thank you.


Some features of ATS will be disabled while you continue to use an ad-blocker.


Can twitter predict a disaster? Early Warning Tweets

page: 1

log in


posted on Sep, 29 2014 @ 09:40 AM
NHK News

The team began by studying tweets made during a storm that cause a landslide in southern Japan 2 years ago.

A number of posts on the day include the phrase "the ground is rumbling," indicating the writers were facing imminent risk. The researchers hope to develop a system that will make the community share that sense of danger and urgency.

Masaru Kunitomo, who joined the team from the National Institute for Land and Infrastructure Management, says the warning signs were published on Twitter almost immediately. "Tweets describing ominous rumblings appeared at the same time as reports of noises from the ground and mountains," he says. "I think it will be useful to collect such information and use it as an early warning sign. It could help us evacuate people."

A computer system will scan tweets for keywords that could indicate landslides, such as "ground rumbling." Alerts would then be sent to local governments, as well as residents.

According to NHK News, Japanese researchers are looking at twitter for that very answer.

There in Japan, right before this latest round of landslides someone noticed some people were posting some rather ominous tweets just 'Before' disaster struck.

“I can feel the ground shaking under my feet”
“I have this copper taste in my mouth”
“The air feels funny today”
“My body feels heavy”

Those researchers are only just now getting started so they have nothing definitive yet. But they say there's a great deal of promise and right now are trying to identify 'key words' that might signal a forth coming disaster. How much warning has yet to be determined but looking at past tweets, there might be up to several days warning, if this all pans out.

They also went on to say that it seems women are better able to make these kinds of predictions. And yet that too is only guesswork due to the generally anonymous nature of twitter.

Again let me say this is all in the very beginning stages of research. Way, way to early to say what if anything will come of it. Yet as a kid, I had an Aunt was always making predictions. Mostly about very mundane things. Still she was right more often than not. Then when you take into account how some animals can tell when an earthquake is about to hit. Well maybe there is something to this twitter deal?
All I can say is, it'll be interesting to see how this all turns out...

posted on Sep, 29 2014 @ 09:51 AM
a reply to: HardCorps

Technically no.
Socially yes of course.

In Japan they even train park rangers and it's rural public to watch the rivers for their catfish that will go a little 'off' before an earthquake, some think it's BS, but it's been that way for hundreds of years apparently.
I am sure they can implement some sort of social media auto mated search engines for key words, or use twitter for certain hash tags, it'll be interesting to see where this will all lead too. The Japanese take earthquakes seriously at all ages there.

posted on Sep, 29 2014 @ 09:56 AM
a reply to: strongfp

Not just earthquakes... right now there all in a tizzy over the Ontake eruption 12 dead and on Monday, yesterday to us... rescuers discovered 5 more unconscious climbers near the summit. That brings the number of victims found in cardiac and respiratory arrest to 24.


seems all their prediction methods failed and there were like 200 climbers on the summit when the eruption took everyone by surprise.

edit on 29-9-2014 by HardCorps because: (no reason given)

posted on Sep, 29 2014 @ 06:36 PM
a reply to: HardCorps
Hiya H.C.-I think so and that youre correct. Using that explaination about how "bots" crawl the internet looking for repetitive and comon words and phrases and their frequency...Im thinking twitter and the like may very well provide some "indicator" of events ahead of them.

new topics

top topics

log in