Social media giant Facebook has revealed how the use of its automated based artificial intelligence to delete terrorism-related posts is producing tremendous results, with photo and video-matching - in feature, which automatically detects previously used imagery by terrorist groups when it is reposted.
Facebook says it does not just look at content but the behaviour behind certain accounts to identify persons posting materials which it does not want on its platform.
The California-based firm said that 99% of the material it now removes about Al Qaeda terrorist group and so-called Islamic State is first detected by itself rather than its users.
But it acknowledged that a lot has to be done towards identifying several groups.
Founder Mark Zuckerberg first detailed his AI-based plan in February.
He revealed at the time that it would take several years to fully develop the required systems.
Facebook initially depends on a combination of human checkers and software to ascertain which posts should be removed, but that the task was now solely being carried out by its automated systems.
This is made possible by the firm sharing hashes unique codes generated from image data with other organisations.
The "digital fingerprints" allow pictures and videos to be swiftly cross-checked against a directory of previously flagged material without the imagery itself which takes up much more data having to be shared.
The firm also referred to text-based machine learning, in which software is trained over time to detect which posts are most likely to be of concern by analysing factors such as the frequency with which certain words and phrases appear.
Facebook said that once a piece of terror content was flagged as being such, it removes 83% of the material and any subsequently uploaded copies within an hour of them being posted.
It added that in some cases, material was now being wiped Further and faster even before it had gone live on its site.
However, this is a cat and mouse game in which those seeking to take advantage of the reach of social media platforms will always look for new ways of getting around these techniques.
Certain types of content, like hate speech, are more difficult to spot with automation and often require human review to understand the context.
UK Prime Minister, Theresa May, along with several other European leaders, has said they desire that terrorist-related material is erased from Facebook within two hours of being posted.
It has been hinted that failure to comply could lead to hefty financial penalties.
.png?auto=webp&format=pjpg&width=3840&quality=60 "Bellingham To The Rescue As Madrid Thump Barcelona In El-Clasico")
