Social media post analysis can now predict potential terrorist acts

Researchers at the University of Bath have uncovered crucial signals in social media posts that can help predict when individuals posting on far-right forums are likely to commit a terrorist act. These posts, often related to logistics, operational planning, and violent action, can reveal a person’s intent up to four years before any criminal behavior takes place. This discovery could have significant implications for preventing terrorist activities.

In a groundbreaking study, published in Personality and Social Psychology Bulletin, the research team compared posts from convicted far-right terrorists with those from individuals holding extremist views who have not committed violence. The majority of offenders in the study were convicted in the United States, making up 75% of the sample. The rest were from the United Kingdom (20%) and a smaller percentage from Australia, Canada, and New Zealand.

Interestingly, the study found that discussing far-right ideology or expressing hateful views did not necessarily indicate that a person would engage in violent action. In fact, the likelihood of mobilization to violence actually decreased when users focused solely on ideology and hate speech.

The findings come at a critical time, as senior police officers in the US and UK have highlighted that an increasing number of individuals turning to terrorism are driven by a fascination with violence rather than deep-rooted ideological fanaticism.

“Our research shows that we can identify people on social media who go on to commit extremist action by picking up on posts that are about acquiring know-how and developing the capability to commit terrorism,” said Dr. Olivia Brown, Associate Professor in Digital Futures at the University’s School of Management and Deputy Director of the Bath Institute for Digital Security and Behaviour. She emphasized that this method could help pinpoint individuals who pose a genuine physical threat, as opposed to those who may only express their extremism through radical views online.

Over a year, the researchers compiled a unique database of more than 200,000 social media posts from 2011 to 2019. This database included posts from 26 individuals convicted of terrorism-related offenses, mostly in the US and the UK, and 48 people sharing extremist content on far-right forums like Iron March, Gab, and Discord, who had not been convicted.

“Unfortunately, the sheer volume of extremist content online means that identifying people most likely to cause harm is like finding a needle in a haystack,” Dr. Brown noted. “We have pinpointed signals of risk to make the haystack smaller and the needle bigger, which can be used to prioritize monitoring resources on a smaller pool of people who we think are more likely to act.”

This approach could offer security services a valuable technological tool, helping to differentiate between individuals likely to engage in terrorist actions and those who are not. While ideological content remains a significant concern, these insights provide an additional layer of understanding to assist in the prevention of extremist violence.

Dr. Brown is now seeking funding to apply these methods to analyze the January 6 Capitol Building riots in the USA, aiming to gain further insights into the mechanisms of mobilization. Additionally, she is collaborating with law enforcement to examine social media posts within the context of online forums, focusing on group interactions, and developing a tool to assess risk within social networks.

This research marks a significant step forward in identifying potential threats and offers a promising approach to enhancing security measures in an increasingly digital world.

Note: Materials provided above by The Brighter Side of News. Content may be edited for style and length.

Like these kind of feel good stories? Get The Brighter Side of News' newsletter.