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.

Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017

Korean HateSpeech Dataset

Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.

Hate Speech Detection Library for Python.

The world's largest social media toxicity dataset.

DeEpLearning models for MultIlingual haTespeech (DELIMIT): Benchmarking multilingual models across 9 languages and 16 datasets.

Code for the paper "Characterizing and Detecting Hateful Users on Twitter"

A Natural Portuguese Language Benchmark (Napolab) for the evaluation of language models.

This repository contains papers and resources pertaining to Hate speech research.

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

Repository for the paper "ViHOS: Vietnamese Hate and Offensive Spans Detection" (EACL2023)

Data and code from our stories, "Google Has a Secret Blocklist that Hides YouTube Hate Videos from Advertisers—But It’s Full of Holes," and "Google Blocks Advertisers from Targeting Black Lives Matter YouTube Videos."

Capstone project to automate Twitter hate speech detection with classification modeling.

Can fear be used for polarisation and spreading negativity? Our paper accepted in The Web conference 2021 tries to explore this question in light of public Whatsapp groups.

iVerify Apps: Apps that support the AI-powered iVerify platform to combat misinformation and hate speech

A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.

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

Intersectional bias in hate speech and abusive language datasets

Code for replicating results of team 'hateminers' at EVALITA-2018 for AMI task