Racist or Sexist Meme? Classifying Memes beyond Hateful

Haris Bin Zia, Ignacio Castro, Gareth Tyson


Abstract
Memes are the combinations of text and images that are often humorous in nature. But, that may not always be the case, and certain combinations of texts and images may depict hate, referred to as hateful memes. This work presents a multimodal pipeline that takes both visual and textual features from memes into account to (1) identify the protected category (e.g. race, sex etc.) that has been attacked; and (2) detect the type of attack (e.g. contempt, slurs etc.). Our pipeline uses state-of-the-art pre-trained visual and textual representations, followed by a simple logistic regression classifier. We employ our pipeline on the Hateful Memes Challenge dataset with additional newly created fine-grained labels for protected category and type of attack. Our best model achieves an AUROC of 0.96 for identifying the protected category, and 0.97 for detecting the type of attack. We release our code at https://github.com/harisbinzia/HatefulMemes
Anthology ID:
2021.woah-1.23
Volume:
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)
Month:
August
Year:
2021
Address:
Online
Venue:
WOAH
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
215–219
Language:
URL:
https://aclanthology.org/2021.woah-1.23
DOI:
10.18653/v1/2021.woah-1.23
Bibkey:
Cite (ACL):
Haris Bin Zia, Ignacio Castro, and Gareth Tyson. 2021. Racist or Sexist Meme? Classifying Memes beyond Hateful. In Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), pages 215–219, Online. Association for Computational Linguistics.
Cite (Informal):
Racist or Sexist Meme? Classifying Memes beyond Hateful (Zia et al., WOAH 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.woah-1.23.pdf
Video:
 https://aclanthology.org/2021.woah-1.23.mp4
Data
Hateful MemesHateful Memes Challenge