Codeq Spotlight

Using AI to identify hate speech on Twitter

Powered by Codeq NLP API




Aggressive and hateful speech online is very disruptive and has a polarizing effect in tone that prevents healthy conversations from taking place.

This issue becomes even more critical and serious, when abusive statements go beyond being offensive and insulting to become instances of hate speech. This dangerous manifestation of verbal abuse is a poison that rots implicit and explicit social contracts and norms and ultimately inspires and incites violence against certain groups.

At Codeq we've built a bot that leverages our verbal abuse detection module to scour Twitter and classify tweets according to whether they contain instances of hate speech or racism.

We believe it is important to make the proliferation of hate speech visible and cast a spotlight on this dangerous phenomenon.

If you're interested in learning more about our abuse detection module we invite you to read about it and give it a try with your own data.

If you would like to contribute to this project, please visit our hateful tweets section that showcases instances of hate speech and give us feedback.

Powered by Codeq NLP API