Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter

Zeerak Waseem, Dirk Hovy


Anthology ID:
N16-2013
Volume:
Proceedings of the NAACL Student Research Workshop
Month:
June
Year:
2016
Address:
San Diego, California
Editors:
Jacob Andreas, Eunsol Choi, Angeliki Lazaridou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
88–93
Language:
URL:
https://preview.aclanthology.org/acl-awards-reasoning/N16-2013/
DOI:
10.18653/v1/N16-2013
Award:
 ACL 2026 Test of Time Award
This paper introduced one of the first, if not the first, and arguably the most influential dataset for studying hate speech detection on social media. It was instrumental in turning our research towards ensuring that our online social lives were minimally impacted by identity-based hatred. Since the publication of this paper, the research in content moderation has helped develop the foundation for automated content moderation systems. The work feels even more important considering how social media has changed over the ensuing 10 years.
Bibkey:
Cite (ACL):
Zeerak Waseem and Dirk Hovy. 2016. Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter. In Proceedings of the NAACL Student Research Workshop, pages 88–93, San Diego, California. Association for Computational Linguistics.
Cite (Informal):
Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter (Waseem & Hovy, NAACL 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/acl-awards-reasoning/N16-2013.pdf