This is a python project that is used to identify hate speech in tweets. The dataset used to train the model is available on Kaggle and consists of labelled tweets where 1 indicates hate speech tweets and 0 indicates non-hate speech tweets.

HateBR is the first large-scale expert annotated dataset of Brazilian Instagram comments for hate speech and offensive language detection on the web and social media.

[USENIX'25] HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns

Towards a Programmable Humanizing AI through Scalable Stance-Directed Architecture

Official repository of HODI, the shared task on Homotransphobia Detection in Italian at Evalita 2023

This repository contains the code and data of the paper titled "XLNet-CNN: Combining Global Context Understanding of XLNet with Local Context Capture through Convolution for Improved Multi-Label Text Classification", which has been accepted at NSysS 2024.

UINSUSKA participation in HASOC 2023 Task 1

In this project, I focused on benchmarking various machine learning models, deep learning architectures, and fine-tuned BERT-based models to evaluate their performance across multiple metrics

It detects caste based hate speech and reinforces social equality and justice

A Python-based data tool for Integrating Hate Speech datasets with varying schemas.

CyberGuard: Machine Learning Vigilance Against Online Harassment

Thesis-McGill

AIceberg - AI learning assistence

Detect hate speech in tweets using NLP and Machine Learning. This project automates classification into hate speech, offensive language, and neutral content. 🐙💻

Hate content moderation bot on Discord

Hate Speech Detection Comparative Study: GPT-3.5 vs. Fine-tuned BERT Model

The rapid growth of social media has led to an increase in user-generated content, making platforms like Twitter a major medium for public communication. However, along with positive engagement, there has also been a surge in hate speech, offensive language, and abusive content. This project aims to address this challenge by developing a ML program

A multilingual lexicon of words to hurt.