SOS: Systematic Offensive Stereotyping Bias in Word Embeddings

Elsafoury, Fatma; Wilson, Steven R.; Katsigiannis, Stamos; Ramzan, Naeem

SOS: Systematic Offensive Stereotyping Bias in Word Embeddings

Elsafoury, Fatma; Wilson, Steven R.; Katsigiannis, Stamos; Ramzan, Naeem

Authors

Fatma Elsafoury

Steven R. Wilson

Dr Stamos Katsigiannis stamos.katsigiannis@durham.ac.uk
Assistant Professor

Naeem Ramzan

Abstract

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. In this [id=stk]work, we introduce a quantitative measure of the SOS bias, [id=stk]validate it in the most commonly used word embeddings, and investigate if it explains the performance of different word embeddings on the task of hate speech detection. Results show that SOS bias exists in almost all examined word embeddings and that [id=stk]the proposed SOS bias metric correlates positively with the statistics of published surveys on online extremism. We also show that the [id=stk]proposed metric reveals distinct information [id=stk]compared to established social bias metrics. However, we do not find evidence that SOS bias explains the performance of hate speech detection models based on the different word embeddings.

Citation

Elsafoury, F., Wilson, S. R., Katsigiannis, S., & Ramzan, N. (2022). SOS: Systematic Offensive Stereotyping Bias in Word Embeddings.

Conference Name	29th International Conference on Computational Linguistics (COLING 2022)
Conference Location	Gyeongju, Republic of Korea
Start Date	Oct 12, 2022
End Date	Oct 17, 2022
Acceptance Date	Aug 16, 2022
Publication Date	2022-10
Deposit Date	Aug 19, 2022
Publicly Available Date	Apr 28, 2023
Pages	1263-1274
Publisher URL	https://aclanthology.org/2022.coling-1.108

Files

Published Conference Proceeding (408 Kb)
PDF

Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/

Copyright Statement
© 1963–2023 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.