JherezTaylor/hatespeech_codewords

A contextual approach for detecting hate speech code words

35
/ 100
Emerging

This project helps social media content moderators and trust & safety teams identify new or subtle forms of hate speech. It takes social media text data and analyzes word usage to detect 'code words' that might be used to circumvent existing moderation tools. The output helps identify emerging hate speech terms that aren't yet in standard dictionaries.

No commits in the last 6 months.

Use this if you need to detect evolving hate speech patterns and code words that evade current keyword-based moderation systems on social media.

Not ideal if you're looking for a simple, off-the-shelf content moderation solution without needing to engage with underlying models or data pipelines.

content-moderation trust-and-safety social-media-monitoring online-harassment policy-enforcement
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

10

Forks

3

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 30, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/JherezTaylor/hatespeech_codewords"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.