Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.

The world's largest social media toxicity dataset.

WhiteLightning distills massive, state-of-the-art language models into lightweight, hyper-efficient text classifiers. It's a command-line tool that lets you create specialized models that run anywhere—from the cloud to the edge—using the universal ONNX format for maximum compatibility.

Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl web service

Resources and tools for the Tutorial - "Hate speech detection, mitigation and beyond" presented at ICWSM 2021

A web-app to identify toxic comments in a youtube channel and delete them.

Improving Indonesian text classification using multilingual language model

(NeurIPS 2022) Official Implementation of Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social-Text Classification

Dataset for identifying potential hates (e.g., political, religious, personal, gender abusive, geopolitical, etc.) for under-resourced Bengali language.

A Nostr relay docker image package which filter content based on content type (SFW/NSFW), user type, language, hate speech (toxic comment), sentiment, topic, and various rules.

Repository for the paper "RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?"

Trained Neural Networks (LSTM, HybridCNN/LSTM, PyramidCNN, Transformers, etc.) & comparison for the task of Hate Speech Detection on the OLID Dataset (Tweets).

Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network

A rule based Hate Speech Detector for Hindi

Developing a classification model to detect hate tweets ready for deployment using various NLP techniques

This is a simple python program which uses a machine learning model to detect toxicity in tweets, developed in Flask.

This is a simple python program which uses a machine learning model to detect toxicity in tweets, GUI in Tkinter.

Developing a classifier to detect instances of racism and xenophobia in English sentences

We are building solutions to stop harrashment and hate speech in online voice communication

Detect hate speech in social media comments using deep learning.