
13 August 2021
AI content moderation systems have the potential to relieve the burden of tackling online hate. But the use of emojis to express hate can outpace what AI systems can understand.
Paul’s research focuses on natural language processing (NLP) methods for detecting online hate speech. He has worked on new techniques for evaluating hate speech detection models, on accounting for language change in NLP models and on managing data annotation for subjective NLP tasks. His wider research interests are in incorporating context (e.g. conversational, social, temporal) as well as subjective perspectives into language modelling.
As part of his DPhil research, Paul has completed research visits to the Alan Turing Institute in London and Bocconi University in Milan, where he worked with Prof Dirk Hovy. Prior to joining the OII in 2019, Paul completed his MPhil in Finance and Economics at the University of Cambridge, where he received a distinction for his thesis using machine learning methods to predict local voting behaviour from online political participation. He also holds a BSc in Economics from Ludwig-Maximilians-University in Munich, Germany.
13 August 2021
AI content moderation systems have the potential to relieve the burden of tackling online hate. But the use of emojis to express hate can outpace what AI systems can understand.
Sky News, 13 August 2021
Harmful posts can end up being missed altogether while acceptable posts are mislabelled as offensive, according to the Oxford Internet Institute. frontpage-pressSky NewsHannah Rose Kirk|Dr Scott A. Hale|Bertram Vidgen|Paul Röttger
BBC News, 18 July 2021
Online hate has been in the headlines again recently due to an avalanche of racist posts directed at three players who missed penalties in England's defeat to Italy in the Euro 2020 final.
Wall Street Journal, 07 June 2021
One of the most comprehensive studies to date on the effectiveness of online hate-speech filters underscores a shortcoming many social-media users know firsthand: They don’t always catch hateful speech.
Professor of Language Modelling, Oxford e-Research Centre, Dept. of Engineering Science., University of Oxford
Professor Pierrehumbert's work has been widely influential in speech technology, psycholinguistics, and theories of language form and meaning.
Professor of Society and the Internet
Helen Margetts is Professor of Society and the Internet, a political scientist specialising in digital government and politics. She was Director of the OII from 2011-18. She is a Professorial Fellow of Mansfield College.