1 code implementation • NAACL (SocialNLP) 2022 • Fatma Elsafoury, Steven R. Wilson, Naeem Ramzan
In recent years, gray social media platforms, those with a loose moderation policy on cyberbullying, have been attracting more users.
no code implementations • COLING 2022 • Fatma Elsafoury, Steve R. Wilson, Stamos Katsigiannis, Naeem Ramzan
Systematic Offensive stereotyping (SOS) in word embeddings could lead to associating marginalised groups with hate speech and profanity, which might lead to blocking and silencing those groups, especially on social media platforms.
no code implementations • ACL 2022 • Fatma Elsafoury
Finally, I investigate the causal effect of the social and intersectional bias on the performance and unfairness of hate speech detection models.
no code implementations • 31 Aug 2023 • Fatma Elsafoury
This paper is a summary of the work done in my PhD thesis.
no code implementations • 21 Aug 2023 • Fatma Elsafoury
Our results suggest that all the inspected LMs are SOS biased.
no code implementations • 22 May 2023 • Fatma Elsafoury, Stamos Katsigiannis, Naeem Ramzan
In this paper, we provide a holistic analysis of the different sources of bias, Upstream, Sample and Overampflication biases, in NLP models.
no code implementations • 16 May 2023 • Fatma Elsafoury, Gavin Abercrombie
In this paper, we trace the biases in current natural language processing (NLP) models back to their origins in racism, sexism, and homophobia over the last 500 years.