Linguistic analysis of pro-ISIS users on Twitter

ABSTRACT

The present study analyzed the differences in the language usage between pro-ISIS users and random users on Twitter. Based on the literature, it was expected that, when comparing the tweets from both samples, distinctive patterns would be found on their usage of similar linguistic categories. This observational study compared a dataset of 105 pro-ISIS users with 91 random Twitter users, both collected between 2015 and 2016. The Linguistic Inquiry Word Count (LIWC) software was employed to analyze the terminology used by both groups from a quantitative perspective. Relevant LIWC categories used in previous studies were included in the assessment. ISIS supporters used significantly more third person plural pronouns and less first person singular and second person pronouns. They also used more words related with death, certainty, and anger than the random group, along with more words containing six letters or more. Finally, more negative language and tone was used by the pro-ISIS group. The language used by ISIS supporters on Twitter was discussed, as well as comparisons to relevant studies on other political extremists. Ultimately, our results suggest that broad similarities in language usage exist between ISIS supporters and other extreme ideologies.

KEYWORDS:

• Twitter
• radicalization
• Linguistics
• ISIS
• political extremism
• jihadism

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

Javier Torregrosa is currently a research assistant at Autonomous University of Madrid. He is currently finishing his PhD studies on Psychology, while he works in multidisciplinary projects with computer engineers, criminologists, and educators. His research topics are focused on the relationship between new technologies and human behaviour, including risk management through online linguistic detection, video games and the emotional impact they have on the player, or how people display their psychological features on their online social networks.

Josh Thorburn is currently a Psychology student at RMIT University in Melbourne, Australia. He has completed a year-long internship at Universidad Autonoma de Madrid (Spain), participating in a project funded by the European Union that researched radicalization on social media. Most recently, Josh has worked as a research assistant for Dr Peter Chambers and Dr Rachel Busbridge on a project exploring the far-right's presence across different media platforms in Australia. Josh's research interests include political extremism, social media, gendered violence and masculinity.

Raúl Lara-Cabrera received the M.Sc. and Ph.D. degrees in Computer Science from the University of Málaga, Spain, in 2013 and 2015, respectively. He is currently a Research Fellow with the IT Systems Department at Technical University of Madrid. His main research areas involve computational intelligence, video games, and complex systems.

David Camacho is currently working as Associate Professor in the IT Systems Department at Technical University of Madrid (Spain) and leads the Applied Intelligence and Data Analysis group (AIDA). He received a Ph.D. in Computer Science (2001) from Universidad Carlos III de Madrid, and a B.S. in Physics (1994) from Universidad Complutense de Madrid. He has published more than 280 journals, books, and conference papers. His research interests include data mining, EvolutionaryComputation (GAGP), MultiAgent Systems and Swarm Intelligence (Ant colonies, ABC, PSO), and Machine Learning (Clustering, HMM, Deep Learning), or Videogames.

Humberto Trujillo works as Full Professor at the University of Granada, on the Department of Methodology for Behavioural Sciences. His main research areas involve terrorism, radicalization and jihadi recruitment. He also works as advisor on several European Projects related with jihadi radicalization.

Notes

1 http://www.fifthtribe.com/.

2 Extra information about the data collection process is published in an interview on the dataset’s webpage: http://blog.kaggle.com/2016/06/03/dataset-spotlight-how-isis-uses-twitter/.

3 While the opposition to the US coalition and to the Al-Assad and Russia alliance is not inherently indicative of support for ISIS, they are useful to focus the attention over certain accounts, especially when using extremist terminology to attack them (for example, ‘Kaffir’ or ‘Crusaders’).

Additional information

Funding

This work was supported by Directorate-General for Justice: [grant number JUST-2015-JCOO-AG/JUST-2015-JCOO-AG-1]; European Commission: [grant number ISFP-2017-AG-RAD]; Ministerio de Economía y Competitividad: [grant number TIN2017-85727-C4-3-P].