Lecture

Abstract - Offensive speech on web platforms is a persistent problem with
wide-ranging impacts. There are many automatic content moderation systems
that detect offensive content on web platforms. However, among many reasons
why these tools fail to eliminate the problem is the reality that people
often disagree on what is offensive. In this talk, I will talk about how
content moderation issues arise in political discussions and how content
moderation research should address them (Weerasooriya et al., EMNLP 2023). 

Speaker information - Dr Tharindu Ranasinghe is a Lecturer at Security and
Protection Science at the School of Computing and Communications, Lancaster
University, where he works with UCREL NLP Group, Data Science Institute
and Security Lancaster. He received his PhD in Computer Science from the
University of Wolverhampton under the supervision of Prof Ruslan Mitkov
and Prof Constantin Orăsan, where he was affiliated with the Research
Group in Computational Linguistics. His research focuses on developing
Machine Learning (ML) approaches for Natural Language Processing (NLP)
tasks, particularly emphasising NLP for Social Good. His work has various
applications, including machine translation, social media analytics (e.g.,
hate speech detection, misinformation detection), and text adaptation.