Predicting online radicalisation

Lead Research Organisation: University of Bath
Department Name: Psychology



An estimated 25,000 foreign fighters have been recruited to Islamic State (IS) from over 100 counties around the world. While shocking in itself, this reflects only the militant end-product of the radicalisation process. Before militancy emerges, IS supporters use mainstream social media in English to socialise, radicalise and recruit foreigners. For example, the fourth IS 'Clanging of the Swords' film racked up millions of views on video-sharing platforms, and created vast excitement among those who followed ISIS online. This use of online communications in English by supporters of Islamic State (IS) presents two unprecedented research opportunities: first, to predict the spread of extremism in English-speaking populations; and second, to understand how online communications shape people's understanding of IS and its opponents. However, currently there is no method to analyse longitudinal social media data to investigate the processes underlying the radicalisation of social media users. The proposed research provides a timely opportunity to refine methods, software and analytics to maximise the impact that psychology and computer science can make to countering extremism. The central research questions are how and why people develop allegiance to extremist groups through communicating online. To do this, we will develop the functionalities and capabilities of an existing software suite that can harvest and analyse large volumes of publicly-available Twitter data ('Tweets').


The central aim of this project is to develop conceptually-grounded social media analytics software to investigate the socialisation and radicalisation of mainstream users. As a by-product of this process, and secondary aim, we will establish how supporters of radical Islam use online communications in English to affect how their target audience defines both themselves and their opponents in relation to IS.


This project will deliver a software tool that can analyse longitudinal big data. This software will be open source and freely available. This means that it will have the potential to make a big impact in social science. It will be applicable to, and usable by, any researcher or practitioner interested in analysing social media data.


Our project brings together a multi-disciplinary team of academics and will be steered by end-users, mediated by Defence Science and Technology Laboratory, whose expertise will enable us to maximise the usefulness and applicability of the software tools. On the academic side, we have assembled a team with interdisciplinary strengths in computer science, psychology and social media data analysis to understand the needs of social scientists and successfully develop technology that will become fully embedded in social science and social media research.

Planned Impact

Four key groups will benefit from this research: policy makers, researchers interested in big data and social media data analysis, government end-users with a security remit, and the general public.

POLICY MAKERS AND RESEARCHERS: We will further develop the existing social media data harvesting and analytics tool, Chorus, to achieve the objectives of the project. Significantly, this product will enable researchers to - for the first time - conduct rigorous longitudinal analysis of the semantic and grammatical content of large N user-driven data. The software will be open-source and freely available, maximising the likelihood that it will achieve impact with this audience. If we achieve wide uptake of these novel software tools by other academics, researchers and practitioners, we will have the potential to create non-academic impact in the policy and practical areas within which they themselves work. For example, health scientists could analyse changes in online users' language over time following an intervention (e.g., the Public Health England 'Stoptober' campaign) that indicates an increase in endorsement of particular behaviours or lifestyle choices. This could be leveraged to change public health policy. Interested researchers and policy makers will be invited onto the Project Advisory Board to maximise the impact that they can have on the project and vice versa.

GOVERNMENT END-USERS: According to the Defence Select Committee's (DSC) report (2015), the UK can and should be playing a greater role in the fight against Islamic State in Iraq and Syria. To respond to this call, this project will directly address the aims of the United in Countering Violent Extremism campaign (#UnitedCVE), which was launched recently by the Organization for Security and Cooperation in Europe (OSCE) to counter the incitement and recruitment of foreign fighters. To engage these stakeholders, plus government end-users from additional agencies, we will invite representatives to workshops at the beginning, middle and end of the project. At these workshops, we will encourage a dialogue with these interested parties to help guide the project, and we will demonstrate the software tools and our findings. Again, interested end-users will also be invited onto the Project Advisory Board. This dialogue will increase both the insight that the research provides and the usefulness of the software to end-users. Through doing so, this research will impact on UK efforts to counter extremism. This may in turn impact on the general public by improving the efficacy of counter-extremism operations in the UK.

POLICY MAKERS AND THE GENERAL PUBLIC: This research has a broad public interest. Therefore, the Project Team will talk about Chorus and the process of online socialisation at accessible forums such as Pint of Science and Ignite, and in media releases via traditional and social media. These contributions will benefit the general public in the longer term through greater and more effective public engagement in understanding the risks associated with online socialisation and radicalisation. Improved understanding of these processes will help social media users navigate the psychological online environment more safely. Greater public understanding will also impact upon the success of policy: where the public is better informed, they can make more informed decisions about policy.


10 25 50

publication icon
Hopthrow T (2020) Rethinking the group: Group processes in the digital age in Group Processes & Intergroup Relations

publication icon
Smith LGE (2020) The Need to Refocus on the Group as the Site of Radicalization. in Perspectives on psychological science : a journal of the Association for Psychological Science

Description While social media interactions are popularly implicated in radicalization, there is no evidence that within-person psychological change occurs through online interactions. A key reason for the absence of such evidence is that there are no viable 'big data' methods to assess whether social media interactions lead to psychological change. We developed a longitudinal paradigm to analyze a sample of 255,062 tweets authored by 110 so-called Islamic State (IS) supporters on Twitter and 109 control users, and investigated the factors associated with within-person increases in radicalism. Results showed that IS supporters conformed to a radical linguistic profile more over time, and to the extent that they engaged in mobilizing interactions with other users on Twitter. This provides evidence that online radicalism increases with mobilizing social media interactions, and validates a new methodological paradigm that can detect and predict the changing trajectory of risk presented by potential terrorist actors online.
Exploitation Route These findings provide the first evidence for online radicalization: specifically, that within-person increases in radicalism occur over time, and are directly related to engagement in mobilizing interactions. We have created and validated a methodology and analytic strategy for extracting longitudinal psychological processes and evidence of within-person change from large samples of social media data. We have demonstrated that a relatively straightforward linguistic analysis can derive the feature vectors for IS classification; and that a linear function can be used to transform lexicon scores into a meaningful psychological factor capturing mobilizing interactions. Our findings and method can potentially be implemented (even automated) to help predict and detect the trajectory of risk presented by potential terrorist actors online. Ultimately, this method can be adapted to any research context in which it is useful to capture within-person psychological change.
Sectors Government, Democracy and Justice,Security and Diplomacy

Description The Foreign and Commonwealth Office have used my Islamic State lexicon in their work to identify and track Islamic State activity online in the MENA region.
First Year Of Impact 2018
Sector Government, Democracy and Justice,Security and Diplomacy
Impact Types Societal,Policy & public services

Description British Academy mid-career fellowship
Amount £88,425 (GBP)
Organisation The British Academy 
Sector Academic/University
Country United Kingdom
Start 09/2016 
End 08/2017
Description Centre for Research and Evidence on Security Threats (CREST)
Amount £4,239,620 (GBP)
Funding ID ES/V002775/1 
Organisation Economic and Social Research Council 
Sector Public
Country United Kingdom
Start 09/2020 
End 09/2023
Description IAA - Predicting Online Radicalization in Arabic
Amount £61,821 (GBP)
Funding ID EPSRC IAA321 
Organisation University of Bath 
Sector Academic/University
Country United Kingdom
Start 08/2018 
End 03/2019
Description The Social Psychology of Online Behaviour
Amount £135,635 (GBP)
Organisation UK Government Investments 
Sector Public
Country United Kingdom
Start 10/2020 
End 03/2021
Title POR data 
Description IS tweets and baseline tweets. 
Type Of Material Database/Collection of data 
Year Produced 2019 
Provided To Others? Yes  
Impact The method developed to model these data has been leveraged for an EPSRC impact acceleration award to apply the method to Arabic social media data. The project partner is the Foreign and Commonwealth Office. 
Description Panel presentation at the United States Institute of Peace 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Policymakers/politicians
Results and Impact This event comprised a public panel discussion about reintegrating extremists, of which I was a panel member and was broadcast via webcast and filmed by Al Jazeera TV. This public panel discussion reached approximately 300 people. There was then a private panel discussion, involving members of the US government and relevant stakeholders.
Year(s) Of Engagement Activity 2020
Description Visit to Cabinet Office 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Policymakers/politicians
Results and Impact I visited the Cabinet Office as an invited expert to contribute to a classified Cabinet Office report on counter-terrorism policy.
Year(s) Of Engagement Activity 2017
Description Visit to Foreign and Commonwealth Office 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Policymakers/politicians
Results and Impact Discussion with FCO officials about results of this project and potential for future collaborative work to automate algorithm for FCO use in the MENA region.
Year(s) Of Engagement Activity 2018
Description Visit to the Home Office (London) 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Policymakers/politicians
Results and Impact I presented a preliminary report on my radicalisation research to the Research, Information, and Communications Unit (RICU) in the Office for Security and Counter-Terrorism (OSCT), The Home Office.
Year(s) Of Engagement Activity 2016