seminars

Analyzing the multiple facets of cyber-aggression and disturbing content on social media

Date
Thursday, December 5, 2019

Time
11.30a.m


Location
ISI seminar room 1st floor

Speaker(s)
Nicolas Kourtellis Research Scientist Telefonica Research

ABSTRACT
=========
In recent years, offensive, abusive and hateful language, sexism, racism and other types of aggressive and cyberbullying behavior and inappropriate or disturbing content 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 disturbing or inappropriate content. Also, 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 behaviors. In these studies, we collect, analyze and annotate user content from Twitter and YouTube, and employ advanced machine and deep learning approaches to detect online aggressive behavior and disturbing content, in its various facets. We use a diverse set of features, extracted from  textual, user and network-related activities of Twitter and YouTube users, and demonstrate that such characteristics can boost the algorithmic  performance for detection of cyber-aggression and disturbing videos targeting kids. Furthermore, we make our collected and annotated datasets and algorithms publicly available for  further research and development by the scientific community.
 
Short Bio:
=========

Dr. Nicolas Kourtellis is a Research Scientist 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 web transparency, user online privacy, leakage of personal data to the online advertising ecosystem and other entities, 2) 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., 3) system design for streaming data analysis and graph mining on distributed streaming processing engines. He has published more than 60 papers, and presented his work in top academic conferences and journals such as IEEE TKDE, IEEE TPDS, IEEE ICDE, ACM KDD, ACM WWW, ACM IMC, ACM/IFIP/USENIX Middleware, 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.).