English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Understanding and Detecting Hateful Content using Contrastive Learning

MPS-Authors
/persons/resource/persons243017

Zannettou,  Savvas
Internet Architecture, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

arXiv:2201.08387.pdf
(Preprint), 5MB

Supplementary Material (public)
There is no public supplementary material available
Citation

González-Pizarro, F., & Zannettou, S. (2022). Understanding and Detecting Hateful Content using Contrastive Learning. Retrieved from https://arxiv.org/abs/2201.08387.


Cite as: https://hdl.handle.net/21.11116/0000-000A-27F9-2
Abstract
The spread of hate speech and hateful imagery on the Web is a significant
problem that needs to be mitigated to improve our Web experience. This work
contributes to research efforts to detect and understand hateful content on the
Web by undertaking a multimodal analysis of Antisemitism and Islamophobia on
4chan's /pol/ using OpenAI's CLIP. This large pre-trained model uses the
Contrastive Learning paradigm. We devise a methodology to identify a set of
Antisemitic and Islamophobic hateful textual phrases using Google's Perspective
API and manual annotations. Then, we use OpenAI's CLIP to identify images that
are highly similar to our Antisemitic/Islamophobic textual phrases. By running
our methodology on a dataset that includes 66M posts and 5.8M images shared on
4chan's /pol/ for 18 months, we detect 573,513 posts containing 92K
Antisemitic/Islamophobic images and 246K posts that include 420 hateful
phrases. Among other things, we find that we can use OpenAI's CLIP model to
detect hateful content with an accuracy score of 0.84 (F1 score = 0.58). Also,
we find that Antisemitic/Islamophobic imagery is shared in 2x more posts on
4chan's /pol/ compared to Antisemitic/Islamophobic textual phrases,
highlighting the need to design more tools for detecting hateful imagery.
Finally, we make publicly available a dataset of 420 Antisemitic/Islamophobic
phrases and 92K images that can assist researchers in further understanding
Antisemitism/Islamophobia and developing more accurate hate speech detection
models.