Cyberbullying Detection System

The goal of this project is to build a community driven cyberbullying detection system.

Datasets:

1. Cyberbullying datasets - Mendeley Data
2. TweetBLM: A Hate Speech Dataset and Analysis of BlackLivesMatter-related Microblogs on Twitter | Zenodo
3. Hate Speech Identification - dataset by crowdflower | data.world
4. Hate Speech Twitter annotations by Waseem and Hovy
5. A Large-Scale English Multi-Label Twitter Dataset for Cyberbullying and Online Abuse Detection - ACL Anthology
6. Cyber Bullying Types Datasets | IEEE DataPort
7. Mendeley Data - Cyberbullying Datasets - sourced from Kaggle, Twitter, Wikipedia Talk pages and YouTube

Resources

1. Training BERT for Cyberbullying Detection - HF Trainer Baseline
2. A Large-Scale English Multi-Label Twitter Dataset for Online Abuse Detection
3. Wikipedia Detox (used by the Mendeley Data)
4. Unsupervised Cyberbullying Detection via Time-Informed Gaussian Mixture Model
5. Towards Understanding and Detecting Cyberbullying in Real-world Images
6. Detection of Cyberbullying Incidents on the Instagram Social Network
7. XBully: Cyberbullying Detection within a Multi-Modal Context

Tech Talks

1. Advancing Cyberbullying Detection with Psychological Insights and Complex Media Data by Lu Cheng

Competitions/Challenges

1. Hateful Memes Challenge by Facebook AI