Online Library

Social media has become an indispensable part of the everyday lives of millions of people around the world. It provides a platform for expressing opinions and beliefs, communicated to a massive audience. However, this ease with which people can express themselves has also allowed for the large scale spread of propaganda and hate speech. To prevent violating the abuse policies of social media platforms and also to avoid detection by automatic systems like Google’s Conversation AI, racists have begun to use a code (a movement termed Operation Google). This involves substituting references to communities by benign words that seem out of context, in hate filled posts or Tweets. For example, users have used the words Googles and Bings to represent the African-American and Asian communities, respectively. By generating the list of users who post such content, we move a step forward from classifying tweets by allowing us to study the usage pattern of these concentrated set of users.

Islamophobic hate speech on social media is a growing concern in contemporary Western politics and society. It can inflict considerable harm on any victims who are targeted, create a sense of fear and exclusion amongst their communities, toxify public discourse and motivate other forms of extremist and hateful behavior. Accordingly, there is a pressing need for automated tools to detect and classify Islamophobic hate speech robustly and at scale, thereby enabling quantitative analyses of large textual datasets, such as those collected from social media. Previous research has mostly approached the automated detection of hate speech as a binary task. However, the varied nature of Islamophobia means that this is often inappropriate for both theoretically informed social science and effective monitoring of social media platforms. Drawing on in-depth conceptual work we build an automated software tool which distinguishes between non-Islamophobic, weak Islamophobic and strong Islamophobic content. Accuracy is 77.6% and balanced accuracy is 83%. Our tool enables future quantitative research into the drivers, spread, prevalence and effects of Islamophobic hate speech on social media.

Online social networks have become a powerful venue for political activism. In many cases large, insular online communities form that have been shown to be powerful diffusion mechanisms of both misinformation and propaganda. In some cases, these groups users advocate actions or policies that could be construed as extreme along nearly any distribution of opinion and are thus called Online Extremist Communities (OECs). Although these communities appear increasingly common, little is known about how these groups form or the methods used to influence them. The work in this thesis provides researchers a methodological framework to study these groups by answering three critical research questions:
• How can we detect large dynamic online activist or extremist communities?
• What automated tools are used to build, isolate, and influence these communities?
• What methods can be used to gain novel insight into large online activist or extremist communities?
This group members social ties can be inferred based on the various affordances offered by OSNs for group curation. By developing heterogeneous, annotated graph representations of user behavior I can efficiently extract online activist discussion cores using an ensemble of unsupervised machine learning methods. I call this technique Ensemble Agreement Clustering. Through manual inspection, these discussion cores can then often be used as training data to detect the larger community. I present a novel supervised learning algorithm called Multiplex Vertex Classification for network bipartition on heterogeneous, annotated graphs. This methodological pipeline has also proven useful for social botnet detection, and a study of large, complex social botnets used for propaganda dissemination is provided as well. Throughout this thesis, I provide Twitter case studies including communities focused on the Islamic State of Iraq and al-Sham (ISIS), the ongoing Syrian Revolution, the Euromaidan Movement in Ukraine, as well as the alt-Right.

Identification and classification of extremist-related tweets is a hot issue. Extremist gangs have been involved in using social media sites like Facebook and Twitter for propagating their ideology and recruitment of individuals. This work aims at proposing a terrorism-related content analysis framework with the focus on classifying tweets into extremist and non-extremist classes. Based on user-generated social media posts on Twitter, we develop a tweet classifcation system using deep learning-based sentiment analysis techniques to classify the tweets as extremist or non-extremist. The experimental results are encouraging and provide a gateway for future researchers.

As the information age comes to fruition, terrorist networks have moved mainstream by promoting their causes via the World Wide Web. In addition to their standard rhetoric, these organizations provide anyone with an Internet connection the ability to access dangerous information involving the creation and implementation of Improvised Explosive Devices (IEDs). Unfortunately for governments combating terrorism, IED education networks can be very difficult to find and even harder to monitor. Regular commercial search engines are not up to this task, as they have been optimized to catalog infor mation quickly and e fficiently for user ease of access while promoting retail commerce at the same time. This thesis presents a performance analysis of a new search engine algorithm designed to help find IED education networks using the Nutch open-source search engine architecture. It reveals which web pages are more important via references from other web pages regardless of domain. In addition, this thesis discusses the potential evaluation and monitoring techniques to be used in conjunction with the proposed algorithm.

Social networks are being used by terrorist organizations to distribute messages with the intention of influencing people and recruiting new members. The research presented in this paper focuses on the analysis of Twitter messages to detect the leaders orchestrating terrorist networks and their followers. A big data architecture is proposed to analyze messages in real time in order to classify users according to diferent parameters like level of activity, the ability to infuence other users, and the contents of their messages. Graphs have been used to analyze how the messages propagate through the network, and this involves a study of the followers based on retweets and general impact on other users. Ten, fuzzy clustering techniques were used to classify users in profiles, with the advantage over other classifcations techniques of providing a probability for each profile instead of a binary categorization. Algorithms were tested using public database from Kaggle and other Twitter extraction techniques. The resulting profiles detected automatically by the system were manually analyzed, and the parameters that describe each profile correspond to the type of information that any expert may expect. Future applications are not limited to detecting terrorist activism. Human resources departments can apply the power of profle identification to automatically classify candidates, security teams can detect undesirable clients in the financial or insurance sectors, and immigration officers can extract additional insights with these
techniques.