Web Scans: Algorithm Predicts ISIS Attacks! Tool sifts through online posts from followers in various languages
Researchers at the University of Miami have developed a new algorithm that searches relevant pages of the terrorist organization ISIS on the Internet and predicts where a new attack is planned.
To create the tool, the scientists analyzed and comprehensively evaluated countless online posts from ISIS supporters in a variety of languages. Around 100,000 ISIS supporters have been identified on the Russian social network Vkontakte.
Good forecasts through tracking
When examining the comments, the Florida experts also found that ISIS terrorists usually form small groups for planned attacks and are not lone perpetrators.
Both the members and the number of members of these communities are constantly changing. The tool was aimed at small, self-organizing ISIS groups that make their mostly radical contributions public for the first time on the Internet. Tracking communication is intended to enable forecasts.
But terrorism experts also have doubts about the usefulness of the new approach. According to the experts, it remains doubtful whether the tool can actually prevent attacks.
In the subsequent analysis of attacks in 2014 and 2015, the model only correctly predicted one attack. Nevertheless, large-scale attack plans in particular could be discovered in a timely manner and thwarted accordingly.
Original description of the tool: http://science.sciencemag.org/content/352/6292/1459.full
Sender: pressetext.redaktion
Article image: Orlok / Shutterstock.com
Notes:
1) This content reflects the current state of affairs at the time of publication. The reproduction of individual images, screenshots, embeds or video sequences serves to discuss the topic. 2) Individual contributions were created through the use of machine assistance and were carefully checked by the Mimikama editorial team before publication. ( Reason )