Measuring Proximity Between Newspapers and Political Parties:
The Sentiment Political Compass

On this website, we provide our paper, the dataset and open-source all code from the Sentiment Political Compass project which we presented at The Internet, Policy & Politics Conference 2018 at the University of Oxford and published in the Journal Policy & Internet. The dataset contains over 740,000 semantically labeled entities from over 180,000 newspaper articles. Further details can be found in the README file in our Github repository. Doing so, we hope that we can encourage further analysis or extending research on our approach, for example in other countries.

We'd be happy to hear what you think about the project and get your feedback! Please drop us a message here.