Hello World,

My name is Fatma Elsafoury and I’m a postdoc at the Weizenbaum institute in Berlin. I joined the Data, Algorithmic Systems and Ethics research group.

Research

In my research, I'm interested in social science computing. 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'm interested in understanding how social biases impact the decisions made by ML models regarding toxicity and hate speech detection.

I’ve been an active member in my community by organising the Women_in_NLP talk series where I have invited 10 women, so far, from Google, Microsoft, Rasa, Allen AI, Carnegie Mellon University and others to discuss their research and share their experience in NLP to encourage more women to work on NLP projects.

To know more about me:

Recent Updates:

  • Jan 2024: I passed my PhD viva with minor corrections. A Link to my PhD thesis after corrections.
  • Oct 2023: My PhD summary paper is accepted at the The Big Picture workshop at EMNLP. The paper is called Thesis Distillation: Investigating The Impact of Bias in NLP Models on Hate Speech Detection
  • Sept 2023: I started my research position at the Weizenbaum research Institute in Berlin.
  • July 2023: I submitted my PhD thesis at the University of the West of Scotland.
  • June-Aug 2022: I did an internship with the NLP group at IBM Research in New York.
  • Aug 2022: My latest paper was accepted at COLING 2022.
  • May 2022: I was awarded an Enrichment Scheme (Community Award) at the Alan Turing Institute in London.