《少数派报告》成真,社交网络预测恐怖袭击

【《少数派报告》成真,社交网络预测恐怖袭击】迈阿密大学教授Johnson开发了一种新的算法,与以往的算法关注激进分子个人发布的言论不同,这种算法通过关注恐怖分子在网上的虚拟团体来预测他们的恐怖行为。在俄罗斯最大的社交网络VK上,通过8个月的观察,发现了196个倾向ISIS的恐怖群体。

Can an algorithm predict terror attacks? Scientists create new method of mining social media to anticipate Isis' next move

23F2B97E00000578-0-image-a-1_1466159302974

A computer algorithm that can identify patterns in the social media activity of Islamic State supporters could provide clues about where terrorist attacks are likely to occur.

Scientists have found they can spot distinct behavioural patterns in the interactions between groups on social media, and it could even help them predict 'lone wolf' attacks'.

Social media has been a key tool for organisations like Isis to help them recruit supporters and coordinate their activities.

 

While law enforcement authorities have attempted to keep track of Isis members using social media, they have tended to focus on monitoring the posts made by individuals.

 

Their attempts are often frustrated by the constant switching of accounts by Isis supporters, which can make it difficult to keep tabs on them.

But the new algorithm produced by Dr Neil Johnson and his team instead attempts to look for group behaviour as users interact on social media.

It allowed them to identify the key groups who were seriously discussing operational details like financing or avoiding drone strikes even though they shifted accounts as they were shut down.

Dr Johnson, a physicist at the University of Miami said: 'It was like watching crystals forming.

'We were able to see how people were materializing around certain social groups. They were discussing and sharing information - all in real-time.'

In a paper published in the journal Science, the researchers describe how they were able to apply mathematical equations used in chemistry and physics to watch pro-Isis groups develop.

They searched through a year's worth of posts on Russian social networking site Vkontakte – which has 350 million users - for pro-Isis statements in a range of different languages.

They then used hashtags and other key words to sift through the posts to find those that were interacting together.

They identified 196 pro-ISIS groups operating during the first eight months of 2015, found most of the 108,000-plus individual members of these self-organized groups probably never met.

But they found that these groups, or aggregates, coalesced and proliferated prior to the onset of real-world events.

 

 

Dr Johnson said: 'So the message is - find the aggregates, or at least a representative portion of them, and you have your hand on the pulse of the entire organization, in a way that you never could if you were to sift through the millions of Internet users and track specific individuals, or specific hashtags.'

The researchers were able to watch as groups reincarnated themselves as their social media accounts were shut down.

The groups would also shut themselves down, go quiet for a while before reappear under a different identity later.

 

The researchers suggest that the police and security services could use this approach to focus their attention on a few groups of serious Isis followers to monitor for a build-up to violence.

They also say their approach could also help them to track individuals who may launch 'lone wolf' attacks, like Omar Mateen, who killed 49 people at a gay nightclub in Orlando last weekend.

It is thought Mateen, who claimed allegiance to Isis, was radicalised online.

Dr Johnson said: 'Our research suggests that any online 'lone wolf' actor will only truly be alone for short periods of time.

'As a result of the coalescence process that we observe in the online activity, any such lone wolf was either recently in an aggregate or will soon be in another one.

'With time, we would be able to track the trajectories of individuals through this ecology of aggregates.'

 

链接:http://www.dailymail.co.uk/sciencetech/article-3646534/Can-algorithm-predict-terror-attacks-Scientists-create-new-method-mining-social-media-anticipate-Isis-move.html


Comments are closed.



无觅相关文章插件