Change-Point Analysis of the Public Mood in UK Twitter during the Brexit Referendum

We study the changes in public mood within the contents of Twitter in the UK, in the days before and after the Brexit referendum. We measure the levels of anxiety, anger, sadness, negative affect and positive affect in various geographic regions of the UK, at hourly intervals. We analyse these affect time series' by looking for change-points common to all five components, locating points of simultaneous change in the multivariate series using the fast group LARS algorithm, originally developed for bioinformatics applications. We find that there are three key times in the period leading up to and including the EU referendum. In each case, we find that the public mood is characterised by an increase in negative affect, anger, anxiety and sadness, with a corresponding drop in positive affect. The hour by hour evolution of public mood in the hours leading up to and following the closure of the polls is further analysed in conjunction with the GBP/EUR exchange rate, finding four change-points in the hours following the vote, and significant correlation between the exchange rate and the affect components tested.