Online Library

VOX-Pol Blog Post.

VOX-Pol Guest Lecture Series, Autumn 2022

Speaker: Dr Bettina Rottweiler

Title: The Functional Link Between Conspiracy Theories and Violent Extremism

In recent decades, information technology went through an explosive evolution, revolutionizing the way communication takes place, on the one hand enabling the rapid, easy and almost costless digital interaction, but, on the other, easing the adoption of more aggressive communication styles. It is crucial to regulate and attenuate these behaviors, especially in the digital context, where these emerge at a fast and uncontrollable pace and often cause severe damage to the targets. Social networks and other entities tend to channel their efforts into minimizing hate speech, but the way each one handles the issue varies. Thus, in this thesis, we investigate the problem of hate speech detection in social networks, focusing directly on Twitter. Our first goal was to conduct a systematic literature review of the topic, targeting mostly theoretical and practical approaches. We exhaustively collected and critically summarized mostly recent literature addressing the topic, highlighting popular definitions of hate, common targets and different manifestations of such behaviors. Most perspectives tackle the problem by adopting machine learning approaches, focusing mostly on text mining and natural language processing techniques, on Twitter. Other authors present novel features addressing the users themselves. Although most recent approaches target Twitter, we noticed there were few tools available that would address this social network platform or tweets in particular, considering their informal and specific syntax. Thus, our second goal was to develop a tokenizer able to split tweets into their corresponding tokens, taking into account all their particularities. We performed two binary hate identification experiments, having achieved the best f-score in one of them using our tokenizer. We used our tool in the experiments conducted in the following chapters. As our third goal, we proposed to assess which text-based features and preprocessing techniques would produce the best results in hate speech detection. During our literature review, we collected the most common preprocessing, sentiment and vectorization features and extracted the ones we found suitable for Twitter in particular. We concluded that preprocessing the data is crucial to reduce its dimensionality, which is often a problem in small datasets. Additionally, the f-score also improved. Furthermore, analyzing the tweets’ semantics and extracting their character n-grams were the tested features that better improved the detection of hate, enhancing the f-score by 1.5% and the hate recall by almost 5% on unseen testing data. On the other hand, analyzing the tweets’ sentiment didn’t prove to be helpful. Our final goal derived from a lack of user-based features in the literature. Thus, we investigated a set of features based on profiling Twitter users, focusing on several aspects, such as the gender of authors and mentioned users, their tendency towards hateful behaviors and other characteristics related to their accounts (e.g. number of friends and followers). For each user, we also generated an ego network, and computed graph-related statistics (e.g. centrality, homophily), achieving significant improvements – f-score and hate recall increased by 5.7% and 7%, respectively.

The emergence and actions of the so-called Islamic State
of Iraq and the Levant (ISIL/ISIS) has received widespread
news coverage across the World, largely due to their capture
of large swathes of land across Syria and Iraq, and the
publishing of execution and propaganda videos. Enticed by
such material published on social media and attracted to the
cause of ISIS, there have been numerous reports of individuals
from European countries (the United Kingdom and France
in particular) moving to Syria and joining ISIS. In this paper
our aim to understand what happens to Europe-based
Twitter users before, during, and after they exhibit pro-ISIS
behaviour (i.e. using pro-ISIS terms, sharing content from
pro-ISIS accounts), characterising such behaviour as radicalisation
signals. We adopt a data-mining oriented approach
to computationally determine time points of activation (i.e.
when users begin to adopt pro-ISIS behaviour), characterise
divergent behaviour (both lexically and socially), and quantify
influence dynamics as pro-ISIS terms are adopted. Our
findings show that: (i) of 154K users examined only 727 exhibited
signs of pro-ISIS behaviour and the vast majority of
those 727 users became activated with such behaviour during
the summer of 2014 when ISIS shared many beheading
videos online; (ii) users exhibit significant behaviour divergence
around the time of their activation, and; (iii) social homophily
has a strong bearing on the diffusion process of proISIS
terms through Twitter.

While the internet provides access to rich educational experiences, great entertainment, and the chance to connect with friends around the clock, it also creates a number of risks that young people, parents, and guardians need to be aware of. There are the commonly known concerns of identity theft, online predators, and cyber-bullying but there is another issue that we need to collectively work to address— Radicalisation to violence. This informational resource strives to increase the awareness of how the internet is being used to radicalise and recruit youth in North America.

The United States is losing the information war to terrorists like ISIS and Hezbollah. Earlier this year, the administration rebranded the office responsible for counter messaging, but little seems to have changed. A strong, effective information offensive to counter the violent ideology being pushed by ISIS and other terrorists is long overdue. This hearing will give members an opportunity to press the administration’s top public diplomacy official on how the U.S. can be more effective.