Loading...
Loading...

Go to the content (press return)

Hate speech in pixels: automatic detection of offensive memes for moderation

Author
Oriol, B.; Canton, C.; Giro, X.
Type of activity
Presentation of work at congresses
Name of edition
Workshop on AI for Social Good 2019
Date of publication
2019
Presentation's date
2019-12-14
Book of congress proceedings
NeurIPS Joint Workshop on AI for Social Good
Project funding
MALEGRA, TEC2016-75976-R
Repository
https://imatge.upc.edu/web/publications/hate-speech-pixels-detection-offensive-memes-towards-automatic-moderation Open in new window
URL
https://aiforsocialgood.github.io/neurips2019/accepted/track1/pdfs/66_aisg_neurips2019.pdf Open in new window
Abstract
This work addresses the challenge of hate speech detection in Internet memes, and attempts using visual information to automatically detect hate speech, unlike any previous work of our knowledge. Memes are pixel-based multimedia documents that contain photos or illustrations together with phrases which, when combined, usually adopt a funny meaning. However, hate memes are also used to spread hate through social networks, so their automatic detection would help reduce their harmful societal impac...
Keywords
Deep learning, Hate speech, Multimodal
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

  • Oriol, Benet  (author and speaker )
  • Canton Ferrer, Cristian  (author and speaker )
  • Giro Nieto, Xavier  (author and speaker )