ECPR

Install the app

Install this application on your home screen for quick and easy access when you’re on the go.

Just tap Share then “Add to Home Screen”

ECPR

Install the app

Install this application on your home screen for quick and easy access when you’re on the go.

Just tap Share then “Add to Home Screen”

To #VoteLeave or #StrongerIn? What Can Twitter Tell us About Cognitive Framing in the EU Referendum Debate

European Politics
Analytic
Social Media
Clare Llewellyn
University of Edinburgh
Laura Cram
University of Edinburgh
Clare Llewellyn
University of Edinburgh

Abstract

As part of the ESRC’s UK in a Changing Europe initiative we are tracking the UK debate on the EU referendum twitter to explore the various ways in which the public imagines the European Union. At a theoretical level, we examine how the debate on the UK’s membership of the EU is being framed and re-framed within the Twittersphere. We ask how this relates to the cognitive frames that predominate in the offline public and political dialogue and explore the process through which competing cognitive frames come to predominate in political debate. Empirically, we have collected data on the EU referendum debate from the Twitter API since August 6th 2015. This data has been gathered using three search strategies, 1) tweets from the full twitter stream, from the percentage made publicly available through the API, 2) tweets collected that contain a set of European Referendum specific terms and 3) tweets collected from specific users, users that we describe as influencers of the debate. This list of influencers includes those that attempt to direct the debate on the referendum, for example, members of parliament (European, UK, Scottish, Welsh and Northern Irish), political journalists, bloggers and think tanks. Methodologically, We use advanced natural language processing and machine learning tools to examine how topics and language differ between these groups and how they influence and cross-pollinate each other. This analysis is publicly accessible through our custom-built interactive demonstrator. We use traditional large-scale cross-sectional surveys to ground the research and to estimate how and to what extent changes in attitudes within Twitter are reflected in mainstream public opinion. In this cutting edge research we explore the limits of current methodologies, tools and techniques for social media analysis and their potential to enhance our understanding of the dynamics of public opinion.