Get dataset for training algorithm to classify cyberbullying tweets




I am currently working on an academic project. The project is to train different supervised learning algorithm for classifying tweets, whether they are cases of cyber bullying or not. I am not able to find dataset for this training. Is there a location where I could find the dataset for the same.


Due to the nature of such data and privacy concerns i’d be surprised if datasets were openly available (I don’t mean tweets themselves - I mean researchers who have gathered examples may be reluctant to share tweet ids publicly for fear of attracting more attention to victims, and also quite a lot of these tweets get deleted)

Might be worth getting in touch with others who work on this topic. Some people I’m aware of that work with such data:,,


Hi @sahayapoorv, were you able to find a cyberbullying tweet dataset? I am working on a similar project and would greatly appreciate it if you could send me any datasets you found. Thank you!