Even after two years of Brexit negotiations no deal between the EU and the UK has been settled. Today, the negotiation’s outcome seems as unpredictable as ever. This paper analyses twitter content as a proxy for the political and public debate with respect to Brexit.
Converging Media versus Diverging Politics - the Brexit Twitter on Debate
Article in CESifo Forum
German Economic Institute (IW)
Even after two years of Brexit negotiations no deal between the EU and the UK has been settled. Today, the negotiation’s outcome seems as unpredictable as ever. This paper analyses twitter content as a proxy for the political and public debate with respect to Brexit.
We analyse all tweets of the remain and leave campaigns to track linguistic changes of the debate over time and to train a Naïve Bayes classifier. By applying this machine learning algorithm, we find increasing approval for the remain side from the media and a further divergence on the Brexit topic between different politicians and groups of politicians after the General Election in July 2017. A particularly alternating position on Brexit can be identified for Jeremy Corbyn, the leader of the Labour Party.
Andrew Bassilakis / Matthias Diermeier / CHenry Goecke: Converging Media versus Diverging Politics - the Brexit Twitter on Debate
Article in CESifo Forum
German Economic Institute (IW)
More on the topic
![The Potential and the Reality in German Companies The Potential and the Reality in German Companies](/fileadmin/_processed_/6/d/csm_Datenbeschaffung_iStock-817442226_e7a096b49b.jpg)
Data Utilisation and Data Sharing: The Potential and the Reality in German Companies
Companies that store their data extensively in digital form, process it in a structured manner and use it in a variety of ways can become particularly efficient members of the data economy.
IW
Intellectual property and fourth industrial revolution technologies: how the patent system is shaping the future in the data-driven economy
Using the classification system from the European Patent Office (EPO), we identify almost 600,000 patent applications for fourth industrial revolution technologies from 1986 to 2015.
IW