younggns/comparative-abusive-lang

This paper conducts a comparative study of various learning models on Hate and Abusive Speech on Twitter dataset. The following script will install required Python packages. We do not provide the code for crawling text data. However, you can ready your dataset by creating crawled_data.pkl While creating the pickle file, you will need to create a python dictionary with the following structure: _dict[_id] [tweet_label, tweet_text, context_text].