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

Abstract

The proximity between newspapers and political parties is strongly subjective and difficult to measure. Yet, political tendencies of newspapers can have a significant impact on voters’ opinion-forming and ought to be known by the public in a transparent and timely manner. This article introduces the Sentiment Political Compass (SPC), a data-driven framework for analyzing political bias of newspapers toward political parties. Using the SPC, newspapers are embedded in a two-dimensional space (left-leaning vs. right-leaning, libertarian vs. autocratic). To assess the informative value of our framework, we crawled a data set consisting of 180,000 newspaper articles from twenty-five newspapers during the German Federal Elections over a time period of 18 months and extracted 740,000 political entities enriched with their contextual sentiment. We analyze this dataset on the party- and politician-level as well as considering the temporal dimension and draw insights about the relationship between newspapers and political parties. We provide the data set and our code open-source at www.politicalcompass.de to encourage the application of the SPC to other political landscapes.