Impact of politically biased data on hate speech classification

This repository contains the source code for the paper:

Impact of politically biased data on hate speech classification

AUTHORS TO BE ADDED AFTER ACCEPTANCE

Data

The GermEval data set can be found here: *2018: https://projects.fzai.h-da.de/iggsa/ *2019: https://github.com/uds-lsv/GermEval-2018-Data

Due to privacy issues, we cannot add the political biased ra data sets to the repository.

Instructions

Clone the repository for full functionality.

A visualisation of the different topics can be found here: data/models/topic_model/topic_model.html

To see the assigned topic for a new tweet in comparison with the topics for the GermEval Dataset have a look at the bottom of the notebook: assign_tweets_to_topic.ipynb

Contact

Feel free to contact us, if you have questions.