Date: 27 March 2018 Time: 12:00
Location: Room 1
Host: Evangelos Markatos
In recent years, offensive, abusive and hateful language, sexism, racism and other types of aggressive and cyberbullying behavior have been manifesting with increased frequency, and in many online social media platforms. In fact, past scientific work focused on studying these forms in popular media, such as Facebook, Twitter, Instagram, Ask.fm, etc. However, these platforms have not adequately addressed the problem of online abusive behavior, and their responsiveness, as well as effective detection and blocking of such inappropriate behavior remain limited. In this talk, I will cover our recent works, in which we propose a set of algorithms to detect and mitigate such complex user behavior. In these studies, we collect, analyze and annotate user content from Twitter, and employ advanced machine and deep learning approaches to detect online aggressive behavior, in its various facets. We use a diverse set of features, extracted from textual, user and network-related activities of Twitter users, and demonstrate that such characteristics can boost the algorithmic performance for detection cyber-aggression. Furthermore, we make our collected and annotated datasets and algorithms publicly available for further research and development by the scientific community. This research has been supported by the Marie Sklodowska Curie RISE EU project, No 691025.
Dr. Nicolas Kourtellis is a Researcher in the Telefonica R&D team, in Barcelona. Previously he was a Postdoctoral Researcher in the Web Mining Research Group at Yahoo Labs, in Barcelona. He holds a Ph.D. in Computer Science and Engineering from the University of South Florida (2012), a MSc in Computer Science from the University of South Florida (2008), and a BSc in Electrical and Computer Engineering from the National Technical University of Athens, Greece (2006). His primary interests lie (1) in the analysis and characterization of online user behavior, with respect to different dimensions such as: abusive, hateful, aggressive and bullying behavior, fake news propagation, fringe online communities, etc., (2) user online privacy, leakage of personal data to the online advertising ecosystem, (3) system design for load balancing of distributed streaming processing engines and streaming graph analysis. He has published more than 40 papers, and presented his work in top academic conferences and journals such as IEEE TKDE, IEEE TPDS, IEEE ICDE, ACM KDD, ACM WWW, ACM/IFIP/USENIX Middleware, ACM IMC, etc., as well as industry-oriented conferences such as Apache BigData in Europe and N. America. He has served in many program committees of top conferences and journals (e.g., WWW, KDD, CIKM, ACM TKDD, IEEE TKDE, IEEE TPDS, etc.).