Overview
- Twitter - largest microblogging website in the world - 330 million global users.
- Content is mostly unrestricted.
-
The Supreme Court has never created any category of speech that is defined by its hateful conduct.
- Hate speech is defined as abusive or threatening speech that expresses prejudice against a particular group, especially on the basis of race, religion, or sexual orientation.
- What is considered ‘hate speech’ is a fine line between the first amendment and harmful conduct unto others.
- With this project, we hope to determine what can be recognized as hate speech on a dataset of over 32,000 tweets.
Inspiration
- 59% of Americans believe online hate and harassment make hate crimes more common.
- 22% feel less safe in their community because of online hate.
- 85% want the government to act by improving training and resources for police on cyber hate.
Data Overview
- Dataset from Kaggle with 31935 records
- 29,695 Non-Hate Labeled Twitter Data (93%)
- 2240 Hate Labeled Twitter Data (7%)