Projects

Hate Crime After Brexit

Funded between 2019 and 2021, this project will link multiple hate crime datasets in the UK, allowing for causal inferences to be made.  A new linked dataset, incorporating both offline and online measures, will allow us to determine if events, like the Brexit vote, caused a genuine increase in hate perpetration. Context of the Project: […]

HateLab: A Global Hub for Data and Insight on Hate Crime and Speech for Policy and Practice

Funded from 2016, HateLab will focus on developing a better understanding of data related to hate crime and speech. Funds will also be used to develop a prototype Online Hate Speech Dashboard that will display aggregate trends of hate speech posted on social media around events, such as Brexit and terror attacks.

HateLab Dashboard

Funded between 2017 and 2020, this project will transform the prototype Online Hate Speech Dashboard into a fully functional version for use by trusted partners.  The Dashboard will be evaluated in a live context, where issues such as performance, accuracy, utility and ethics will be fully examined.

Understanding Online Hate Speech as a Motivator for Hate Crime

Funded between 2016 and 2019, this project will investigate the utility of Twitter data for understanding what types, for whom, and where online hate speech acts a ‘signature’ of offline hate crime. The study will develop a statistical model that links anonymous aggregate online hate speech and offline hate crimes, using tweets and reported hate crimes […]

Hate Speech and Social Media

Funded between 2013 and 2014, this project developed a range of machine learning classifiers designed to identify online hate speech across the protected characteristics of race, religion, sexual orientation and disability.  These classifiers were used in the first study of online hate speech produced in the aftermath of a terrorist event. Using Big Data to […]

Social Media and Prediction: Crime Sensing, Data Integration and Statistical Modelling

This project ran between 2013 and 2015, and aimed to test if social media data could be used to  estimate crime patterns at an aggregate level.  Data were collected over 12 months generating 180 million geocoded tweets and close to 600,000 Metropolitan Police recorded crime incidents.  The ethics of using social media in crime and security […]