New computer algorithm might be able to predict the next ISIS attack
So ISIS and its supporters have been highly successful in carrying out terrorist attacks through out the globe with impunity. Their success has much to do with the incoherent policies of world which have not united to take not the terror threats. However, now science is looking to fill the void and predict next ISIS terror attacks.
A group of physicists from University of Miami have come together to build a algorithm which will predict when and where the dreaded ISIS terrorists strike again. Neil Johnson, a physicist at the University of Miami, assembled a team and over few months they created an algorithm to sift through the pro-terrorism vitriol that populates the internet.
It is a well known fact that ISIS and its cadres are using their online presence increasingly to mount terror attacks. They use Facebook, Twitter, Telegram etc. to communicate with their cadres and also propagate their organisation.
While Facebook and Twitter doing a pretty good job of blocking pro-ISIS or other terrorist groups, the ISIS cadres are still effectively using these and other tools to communicate and propagate. This is proved by the fact that, Orlando killer, Omar Mateen posted Islamic State-related threats on Facebook and allegedly used the social media platform to search for information on the San Bernardino terrorists last month, according to a Senate Committee.
If there was a dedicated software to sift through millions of posts, mentions, tweets, Mateen could have been identified well before the attack. This is the void that Johnson and his colleagues seek to fill. Though the new software would have more thrust on group attacks. The new research in Science Magazine shows lone actors shouldn’t be the top priority when it comes to tracking ISIS online – groups should.
The team published a study yesterday in the journal Science that showed its work in looking for pro-ISIS posts in multiple languages on the Russia-based social media service that is a “European equivalent” of Facebook called Vkontakte. While their work is appreciated by experts, the same experts point out that data-mining for words like “beheading” and “infidels” even with an algorithm does not make identifying the potential for an attack any easier.
“This is an interesting approach, this is a potentially valuable approach, and more research should be done on the approach,” said J. M. Berger, a fellow in George Washington University’s Program on Extremism and the co-author of “ISIS: The State of Terror.” speaking with the New York Times. “But to jump ahead to the utility of it, I think, takes more work.”
The physicists say that their algorithm could help law enforcement track those that might wish to travel to ISIS controlled territory in order to train with the group or sympathise remotely about their liking for ISIS and its world domination methods.
Dr. Johnson recognises this but also believes that his study has a goal and that was to get “a proper quantitative science of online extremism to replace the black-box narrative that is currently used.” Johnson and his work looked to focus on smaller groups whose chat got more heated recently rather than look at millions under the single umbrella of supporting groups like ISIS.
It’s easy to forget sometimes that humans are part of nature itself and “the way transitions happen is like a flock of birds, a school of fish,” said Johnson.
“There’s no one fish saying, ‘Hey, I want everyone to be about five inches away from someone else, and we’re going to have this shape,’ ” he said.
Vkontakte has a user base of roughly 350 million people and doesn’t much seem to mind that pro-ISIS sites popup nearly everyday. Additionally, the social media site includes a number of Chechen members that have been targeted specifically with ISIS propaganda. In addition to the algorithm, the team worked with experts in covert groups who also spoke Spanish, Chinese, Arabic, French, German, and Russian in addition to English.
The post Physicists develop computer algorithm to predict next ISIS terror attack appeared first on TechWorm.