9:00 Welcome & introduction – Theodora Tsikrika, CERTH, Greece
9:30 Invited talk: Tackling online hate – a collaborative approach
Gwanwyn Mason, Programme Manager for Hate Crime, Mayor’s Office for Policing And Crime (MOPAC), London, UK
10:30 Coffee break
11:00 Linguistic Markers of a Radicalized Mind-set Among Extreme Adopters
Katie Cohen, Tim Isbister, Lisa Kaati and Amendra Shrestha
11:30 Evasive Focused Crawling by Exploiting Human Browsing Behaviour: a Study on Terrorism-Related Content
Christos Iliou, Theodora Tsikrika, Stefanos Vrochidis and Ioannis Kompatsiaris
12:00 A Platform for Knowledge Retrieval, Discovery & Analysis of Online Homemade Explosives Resources
Dimitrios Pappas, George Kalpakis, Iraklis Paraskakis, Stefanos Vrochidis and Ioannis Kompatsiaris
12:30 Lunch break
14:00 Invited talk: Classifying and Modeling Cyber Hate Speech: Research and Opportunities for Practical Intervention
Dr. Pete Burnap and Professor Matt Williams, Directors – Social Data Science Lab, Cardiff University, UK
Hateful and antagonistic content published and propagated via the World Wide Web has the potential to cause harm and suffering on an individual basis, and lead to social tension and disorder beyond cyber space. Despite new legislation aimed at prosecuting those who misuse new forms of communication to post threatening, harassing, or grossly offensive language – or cyber hate – and the fact large social media companies have committed to protecting their users from harm, it goes largely unpunished due to difficulties in policing online public spaces. To support the automatic detection of cyber hate online, specifically on Twitter, we build multiple individual models to classify cyber hate for a range of protected characteristics including race, disability and sexual orientation. We use text parsing to extract typed dependencies, which represent syntactic and grammatical relationships between words, and are shown to capture ‘othering’ language – consistently improving machine classification for different types of cyber hate beyond the use of a Bag of Words and known hateful terms. Furthermore, we build a data-driven blended model of cyber hate to improve classification where more than one protected characteristic may be attacked (e.g. race and sexual orientation), contributing to the nascent study of intersectionality in hate crime. We conclude by presenting future challenges and opportunities for cyber hate research on the Web.
14:45 Invited talk: A System for Detecting Malicious Online Messages
Dr. Edward Apeh, Bournemouth University
Cyberspace has fostered the emergence of an increasingly globalized world in which individuals can create and build interactions at the click of a button. This has served in promoting the development of shared spaces in which complex interactions can take place and be facilitated. Many of these interactions tend to be healthy and mutually beneficially to all the interacting participants. Increasingly, however, cyberspace is being used for preying on the vulnerable by individuals who create interactions for the sole purpose of exerting emotional, ideological or physical pressure on others. The increasing development of such interactions have facilitated the growth of cyber-bullying in which vulnerable individuals are attacked. To curb the rapid growth of such interactions, there is a need for systems for safeguarding vulnerable individuals from such interactions. Policies, code of practices and automated techniques have been put in place to little effect in curtailing the surge of cyber-bullying. This paper presents an investigation into the problem of cyber-bullying and proposes a system for protecting vulnerable individuals online by intercepting and blocking or reporting malicious messages.
15:30 Coffee break – Workshop end