I am working on an NLP project about classifying offensive text data in social media. By offensive I especially mean threat words that one say to another.

Some examples:

"Stop doing this or else you will pay for it."

"Just wait until you see what's coming"

"I will break your legs next time I see you."

As an initial approach, I considered semantic and syntactic keyword matching. However, doing this on this very problem seemed harder because threating is an action and it is expressed in so many different ways.

My main goal is classifying text data by offensive/non-offensive text by using Machine Learning and Deep Learning algorithms. After weeks of online searching, I could not find a ready-to-use dataset. I considered manually labelling the data. However, I don't know where I should start.

What would be the best approach for making progress in this task? I also plan to do this in both English and German languages.

Also, below is a related article for fully understanding of the problem:
Deep learning for detecting inappropriate content in text


1 Answer 1


Toxic comment classification challenge might be a good place to start. It contains a set of comments and 6 binary classifications indicting if it's a toxic comment and of which type.

I imagine this would be a sufficient start.

  • $\begingroup$ After checking the challenge details, I found that one of the classes is "threat". So it will definitely be helpful for me. Thanks! $\endgroup$
    – Kerem
    Commented Mar 19, 2018 at 21:10
  • $\begingroup$ I checked the dataset and tested it with some popular kernels. It has been a great start for classifying threats. Thank you again. $\endgroup$
    – Kerem
    Commented Mar 22, 2018 at 8:49

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.