zake7749/DeepToxic

top 1% solution to toxic comment classification challenge on Kaggle.

49
/ 100
Emerging

This project helps online communities and content moderators automatically identify and filter harmful content. It takes raw user comments or forum posts as input and classifies them by types of toxicity (like insult, threat, or obscenity), outputting flagged content for review. Community managers, social media platforms, and forum administrators would find this useful for maintaining a safe online environment.

191 stars. No commits in the last 6 months.

Use this if you need to automatically detect and categorize toxic language in user-generated text, such as comments or forum discussions.

Not ideal if your primary concern is real-time moderation of live streams or highly nuanced content that requires deep contextual understanding beyond basic toxicity.

content-moderation online-community-management social-media-management brand-safety text-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

191

Forks

68

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 06, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zake7749/DeepToxic"

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