The UK-based company ASI Data Science unveiled a machine learning algorithm Wednesday that can identify terrorist propaganda videos with 99 percent accuracy.
This development marks one of the first instances of a company successfully using A.I. to flag extremist propaganda. The Islamic State group is notorious for its social media recruiting efforts, and this algorithm could help curtail them.
While the researchers at ASI wouldn’t discuss any technical specifics of the algorithm, it appears to work like other kinds of A.I. recognition software. The algorithm can examine any video and determine the probability that the video is a piece of extremist propaganda. According to the BBC, the algorithm was trained on thousands of hours of terrorist recruiting videos, and it uses characteristics from these videos to assign probability scores.
If a video is marked as very high probability, it is tagged for review by a human content moderator. Because the videos aren’t automatically taken down, any false positive should be caught before the video is wrongfully removed. ASI said that the algorithm could detect up to 94 percent of Islamic State uploads.
The algorithm, which has partially funded by the British government, was mainly created for the benefit of smaller video platforms that don’t have the resources to maintain a large content moderation staff. Because these sites can’t thoroughly examine every video uploaded, it’s easier for terrorist groups to plant propaganda on them. As researcher Marc Warner of ASI told the BBC, “There’s over 1,000 different videos on over 400 different platforms.”
It’s not clear when the new algorithm will be deployed on these sites. When it finally becomes available, groups like the Islamic State will likely try to change the way they craft their videos in order to avoid detection.
Hopefully the computer scientists can stay one step ahead.