Twitter eyed as fast, cheap earthquake alert

After having proven its worth as a fast, real-time messaging platform, micro-blogging service Twitter is being eyed as a detection and warning tool against earthquakes.

 

Japanese scientists have developed a tweet-based quake-reporting system dubbed Toretter, which they said works faster than their country's own official earthquake warnings.

 

"We proved that a social media user could be treated as a sensor and could be applied to earthquake observation," lead researcher Takeshi Sakaki, from the University of Tokyo told SciDev.Net.

 

Citing data from more than 1,000 earthquakes between 2009 and 2011, the researchers found their system detected 93 percent of Japan's strong earthquakes by monitoring tweets.

 

However, the system is not perfect - there was a "large number" of false alarms.

 

Still, the tweet-based system can triggers an early alarm that can give residents enough time to prepare.

 

The system uses computer-based semantic analysis using keywords like "shaking" or "earthquake."

 

It also uses information about when and where each tweet is sent to determine a quake's time and location, and then emails an alert within two minutes of an earthquake.

 

Developing world

 

The researchers are eyeing such a low-cost observation system for the developing world to detect typhoons, tornados, tsunamis and even heavy traffic.

 

This is particularly useful for quake-prone countries with a high number of Twitter users, such as Indonesia.

 

Adam Acar, professor of communication and social media at the Kobe City University of Foreign Studies, Japan, said a Twitter-based system would be an affordable tool in developing countries that do not have comprehensive early-warning systems.

 

"Having an algorithm that constantly checks for sudden increases in the use of certain words — such as quake, shaking, flood, fire — on Twitter is certainly cheaper than hiring many people or building a number of facilities. It may not be 100 percent reliable, but it's definitely better than nothing," he said.

 

Fine-tuning

 

Rapid data processing is still needed to make the alerts accurate, though fine-tuning allowed the system to detect 80 percent of strong earthquakes - with 75 percent of the alarms being accurate.

 

Acar also said Twitter "should be used to supplement existing official information rather than replace it."

 

Doubters

 

On the other hand, Nicholas Sitar, professor of civil and environmental engineering at the University of California, Berkeley, voiced doubts about the system benefiting developing nations.

 

Sitar said a very sophisticated network of sensors and high-speed data processing will be needed to ensure the delivery of useful warnings.

 

"Twitter is just one in a suite of information-delivery systems. The real issue is whether the information can be analysed, interpreted and forwarded sufficiently fast," he said.

 

"This is not some kind of a magic bullet that makes up for the lack of safe construction practices in seismically active parts of the developing world," he added. — TJD, GMA News