Hironsan/HateSonar
Hate Speech Detection Library for Python.
This tool helps social media managers, community moderators, or content creators automatically identify hate speech and offensive language in written text. You provide text content, and it returns a classification of whether it contains hate speech, offensive language, or neither, along with confidence scores for each. This allows teams to quickly flag and address problematic content.
193 stars.
Use this if you need to automatically screen text for hate speech or offensive content without manually reviewing every piece.
Not ideal if you need to detect nuanced forms of harassment or require a highly customized understanding of 'hate speech' for a specific, niche community.
Stars
193
Forks
38
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Hironsan/HateSonar"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
t-davidson/hate-speech-and-offensive-language
Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive...
franciellevargas/HateBR
HateBR is the first large-scale expert annotated dataset of Brazilian Instagram comments for...
rishabhmisra/News-Headlines-Dataset-For-Sarcasm-Detection
High quality dataset for the task of Sarcasm Detection
b4k0/CBDA
Cyber Bullying Detection Application (CBDA)
raklugrin01/Disaster-Tweets-Analysis-and-Classification
Analysing Disaster related tweets dataset and build a classifier using deep learning and deploy...