Online Library

Online social media platforms generally attempt to mitigate hateful expressions, as these comments can be detrimental to the health of the community. However, automatically identifying hateful comments can be challenging. We manually label 5,143 hateful expressions posted to YouTube and Facebook videos among a dataset of 137,098 comments from an online news media. We then create a granular taxonomy of different types and targets of online hate and train machine learning models to automatically detect and classify the hateful comments in the full dataset. Our contribution is twofold: 1) creating a granular taxonomy for hateful online comments that includes both types and targets of hateful comments, and 2) experimenting with machine learning, including Logistic Regression, Decision Tree, Random Forest, Adaboost, and Linear SVM, to generate a multiclass, multilabel classification model that automatically detects and categorizes hateful comments in the context of online news media. We find that the best performing model is Linear SVM, with an average F1 score of 0.79 using TF-IDF features. We validate the model by testing its predictive ability, and, relatedly, provide insights on distinct types of hate speech taking place on social media.

Social media systems allow Internet users a congenial platform to freely express their thoughts and opinions. Although this property represents incredible and unique communication opportunities, it also brings along important challenges. Online hate speech is an archetypal example of such challenges. Despite its magnitude and scale, there is a significant gap in understanding the nature of hate speech on social media. In this paper, we provide the first of a kind systematic large scale measurement study of the main targets of hate speech in online social media. To do that, we gather traces from two social media systems: Whisper and Twitter. We then develop and validate a methodology to identify hate speech on both these systems. Our results identify online hate speech forms and offer a broader understanding of the phenomenon, providing directions for prevention and detection approaches.

VOX-Pol Blog post.

Terrorists and extremists are increasingly utilizing Internet technology to enhance their ability to influence the outside world. Due to the lack of multi-lingual and multimedia terrorist/extremist collections and advanced analytical methodologies, our empirical understanding of their Internet usage is still very limited. To address this research gap, we explore an integrated approach for identifying and collecting terrorist/extremist Web contents. We also propose a Dark Web Attribute System (DWAS) to enable quantitative Dark Web content analysis from three perspectives: technical sophistication, content richness, and Web interactivity. Using the proposed methodology, we identified and examined the Internet usage of major Middle Eastern terrorist/extremist groups. More than 200,000 multimedia Web documents were collected from 86 Middle Eastern multi-lingual terrorist/extremist Web sites. In our comparison of terrorist/extremist Web sites to US government Web sites, we found that terrorists/extremist groups exhibited similar levels of Web knowledge as US government agencies. Moreover, terrorists/extremists had a strong emphasis on multimedia usage and their Web sites employed significantly more sophisticated multimedia technologies than government Web sites. We also found that the terrorists/extremist groups are as effective as the US government agencies in terms of supporting communications and interaction using Web technologies. Advanced Internet-based communication tools such as online forums and chat rooms are used much more frequently in terrorist/extremist Web sites than government Web sites. Based on our case study results, we believe that the DWAS is an effective tool to analyse the technical sophistication of terrorist/extremist groups’ Internet usage and could contribute to an evidence-based understanding of the applications of Web technologies in the global terrorism phenomena.

Research examining radical visual communication and its manifestation on the trending platform TikTok is limited. This paper presents a novel methodological framework for studying mobilization strategies of far-right groups on TikTok, employing a mixed-method approach that combines manual annotation, unsupervised image classification, and named-entity recognition to analyze the dynamics of radical visuals at scale. Differentiating between internal and external mobilization, we use popularity and engagement cues to investigate far-right mobilization efforts on TikTok within and outside their community. Our findings shed light on the effectiveness of unsupervised image classification when utilized within a broader mixed-method framework, as each observed far-right group employs unique platform characteristics. While Conspiracists flourish in terms of overall popularity and internal mobilization, nationalist and protest content succeeds by using a variety of persuasive visual content to attract and engage external audiences. The study contributes to existing literature by bridging the gap between visual political communication at scale and radicalization research. By offering insights into mobilization strategies of far-right groups, our study provides a foundation for policymakers, researchers, and online platforms to develop proactive measures to address the risks associated with the dissemination of extremist ideologies on social media.

Researchers and policymakers have supported a public health approach to countering violent extremism throughout the War on Terror. However, barriers to obtaining primary data include concerns from minority groups about stigmatization, the ethics of harming research subjects by exposing them to violent content, and restrictions on researchers from institutions and governments. Textual analyses of declassified documents from government agencies may overcome these barriers. This article contributes a method for analyzing the predisposing, precipitating, and perpetuating factors of terrorism through open source texts. This method is applied to FBI interrogation summaries of Al Qaeda terrorist Umar Farouk Abdulmutallab who attempted an attack aboard an airplane in 2009. This analysis shows that consuming militant content online led him to narrow his social relationships offline to extremists and foster identifications with subjugated Muslims around the world. After deciding to wage militancy, loyalty to Al Qaeda members, swearing allegiance to and obeying group leaders, and interpreting religious texts militantly perpetuated violent activities. Such work can advance empirical work on militant behavior to develop interventions.