Exploring linguistic features for extremist texts detection (on the material of Russian-speaking illegal texts)

Devyatkin, Dmitry; Smirnov, Ivan V.; Margarita, Ananyeva; Maria, Kobozeva; Chepovskiy, Andrey; Fyodor, Solovyev

doi:10.1109/isi.2017.8004907

Cited by 11 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We then select the top scoring grams to be used as features for the language model. Ngrams and words frequency have been used in the literature to classify similar problems, such as hate-speech and extremist text and have proven successful [17]. The second method we use is word embeddings to capture semantic meanings.…”

Section: A Feature Engineeringmentioning

confidence: 99%

Understanding the Radical Mind: Identifying Signals to Detect Extremist Content on Twitter

Nouh

Nurse

Goldsmith

2019

2019 IEEE International Conference on Intelligence and Security Informatics (ISI)

View full text Add to dashboard Cite

The Internet and, in particular, Online Social Networks have changed the way that terrorist and extremist groups can influence and radicalise individuals. Recent reports show that the mode of operation of these groups starts by exposing a wide audience to extremist material online, before migrating them to less open online platforms for further radicalization. Thus, identifying radical content online is crucial to limit the reach and spread of the extremist narrative. In this paper, our aim is to identify measures to automatically detect radical content in social media. We identify several signals, including textual, psychological and behavioural, that together allow for the classification of radical messages. Our contribution is threefold: (1) we analyze propaganda material published by extremist groups and create a contextual text-based model of radical content, (2) we build a model of psychological properties inferred from these material, and (3) we evaluate these models on Twitter to determine the extent to which it is possible to automatically identify online radical tweets. Our results show that radical users do exhibit distinguishable textual, psychological, and behavioural properties. We find that the psychological properties are among the most distinguishing features. Additionally, our results show that textual models using vector embedding features significantly improves the detection over TF-IDF features. We validate our approach on two experiments achieving high accuracy. Our findings can be utilized as signals for detecting online radicalization activities.

show abstract

Section: A Feature Engineeringmentioning

confidence: 99%

Understanding the Radical Mind: Identifying Signals to Detect Extremist Content on Twitter

Nouh

Nurse

Goldsmith

2019

2019 IEEE International Conference on Intelligence and Security Informatics (ISI)

View full text Add to dashboard Cite

show abstract

“…Analistas del discurso y lingüistas han estudiado estos discursos con objetivos distintos pero complementarios que contribuyen a una comprensión holística del fenómeno. Contamos, por ejemplo, con estudios que identifican características lingüísticas y discursivas para la detección automática de discursos de extrema derecha o izquierda difundidos en medios digitales (Devyatkin et al 2017;Longhi 2020; Alava, Chaouni y Charles 2020), así como estudios sobre la relación entre terrorismo y comunicación desde la amplia perspectiva del análisis del discurso (Matusitz 2013), y otros que se proponen "to understand the way that discourse shapes and is shaped by sociopolitical activity in response to 9/11, war and terrorism" (Hodges y Nilep 2007: 3).…”

Section: Discurso Y Terrorismounclassified

“…responden a la voluntad divina se sustenta en y reproduce el concepto de yihad recurrente en los discursos de captación terrorista (Fuentelsaz Franganillo 2019;cf. Lorenzo-Penalva Lucas 2013;Cook 2015). Según esta interpretación politizada del término yihad, sería una obligación de los creyentes en la religión islámica el practicar la violencia contra el mundo occidental, dado que este amenazaría la integridad fundamental del islam (Smith 2007: 14).…”

Section: Perspectivizaciónunclassified

La construcción discursiva de identidades de terroristas del 17A

Giménez García,

Queralt

2023

Boletín de Filología

View full text Add to dashboard Cite

The literature on jihadist discourse focuses on the processes of propaganda and recruitment and on their dissemination through digital media. On the first session of the trial for the Barcelona and Cambrils attacks of August 17 and 18, 2017 (known as 17A), three videos were screened in which some of the young men who would later become responsible for the attacks convey their intentions while manufacturing explosives. This study analyzes their interaction from the perspective of pragmatic linguistics and examines the identities that the young terrorists construct for themselves and for others through the analytical model put forward in Stamou (2018). The results of this analysis scrutinize the linguistic resources used by the speakers to construct identities for themselves and others, as well as the relations established between these and the ideologies that support their discourse. We conclude that the analytical tools applied in this study may become very relevant for the discoursive and linguistic profiling of alleged terrorists for forensic purposes.

show abstract

“…Further exploration into hybrid models combining multiple ML algorithms or integrating ML with traditional rule-based methods could leverage the strengths of both approaches. Moreover, the integration of ML with Natural Language Processing (NLP) and sentiment analysis techniques could offer a more nuanced understanding of extremist narratives and rhetoric [47].…”

Section: Future Perspectivesmentioning

confidence: 99%

Social Media Mining to Detect Online Violent Extremism using Machine Learning Techniques

Mussiraliyeva¹,

Bagitova²,

Sultan³

2023

IJACSA

View full text Add to dashboard Cite

In this paper, we explore the challenging domain of detecting online extremism in user-generated content on social media platforms, leveraging the power of Machine Learning (ML). We employ six distinct ML and present a comparative analysis of their performance. Recognizing the diverse and complex nature of social media content, we probe how ML can discern extremist sentiments hidden in the vast sea of digital communication. Our study is unique, situated at the intersection of linguistics, computer science, and sociology, shedding light on how coded language and intricate networks of online communication contribute to the propagation of extremist ideologies. The goal is twofold: not only to perfect detection strategies, but also to increase our understanding of how extremism proliferates in digital spaces. We argue that equipping machine learning algorithms with the ability to analyze online content with high accuracy is crucial in the ongoing fight against digital extremism. In conclusion, our findings offer a new perspective on online extremism detection and contribute to the broader discourse on the responsible use of ML in society.

show abstract

Exploring linguistic features for extremist texts detection (on the material of Russian-speaking illegal texts)

Cited by 11 publications

References 9 publications

Understanding the Radical Mind: Identifying Signals to Detect Extremist Content on Twitter

Understanding the Radical Mind: Identifying Signals to Detect Extremist Content on Twitter

La construcción discursiva de identidades de terroristas del 17A

Social Media Mining to Detect Online Violent Extremism using Machine Learning Techniques

Contact Info

Product

Resources

About