KTP Research associate

Hello, my name is Fatma Elsafoury and I’m a second-year Ph.D. student at the University of the West of Scotland.


In my research, I’m interested in social science computing and in particular, social bias, toxicity, hate speech, and fairness. My research interests stem from being a woman from an underrepresented group of people. I understand from my personal and research experiences how bias in NLP and ML applications has a direct impact on the lives of the under-represented groups of people and how hate speech towards minorities has severe implications on society like hate crimes. I believe that these topics are crucial to study now more than ever for building models and communication platforms that are safe, and accessible to all people regardless of their gender, ethnicity, belief, or sexual orientation. In particular, I’m interested in understanding how social biases impact the decisions made by machine learning models regarding toxicity and hate speech detection. In particular, I’m working on a very important and interesting research question, What is the effect of social and intersectional biases on the task of hate speech and abuse detection?

To answer this research question, I’m investigating using casual inference to understand the effect of bias in pre-trained contextual word embeddings and the bias in datasets on the task of hate speech and abuse detection. I’m also investigating how harmful that bias is on the model’s predictions. Finally, I’m investigating the different debiasing methods and weather or not they are effective and what to look out for to build an effective debiasing method.

To know more about me: