Tweeting Brexit

The rise of the digital world is changing how people participate in political debate and activism. It can draw people closer to politics, help to inform the debate, and present new avenues for politicians, journalists and citizens to talk to each other.

This digital political space provides profound access to millions of voices that together form society’s constant political debate. What is more, it gives the possibility of analysing and understanding them, even without any pre-existing knowledge.

In an effort to demonstrate how the analysis of social media can bring insights into the influence of those in the political sphere, or any sphere for that matter, we collected approximately 300 thousand Tweets relating to the “Brexit” Referendum during the last week of March in the UK.

Our Analysis

We looked at three things specifically:

1. Overall influence – measured by combining the quantity of connections (retweets, mentions, replies), the quality of the connections (measured by Page Rank) and the reach of the user’s tweets, which were adjusted to discount the skew towards users with very large number of followers.

2. Connectors – measured using an algorithm called Betweenness Centrality and measures how well a user is connected to all other users compared with everyone else.

3. Interesting metric – used to find smaller users who made a relatively high impact, which is useful for finding niche or local stories in a large network where they are difficult to find. It compares how well a user does in the overall ranking compared to how well they would be expected to do given the number of followers they have.

The Network Map

We mapped the network of those tweeting Brexit to see what the two sides of the debate look like. What is noticeable from the map is that the two main groups are not simply the two sides of the debate but, rather, a strongly united ‘Leave’ group and a group consisting of ‘Remain’ together with a wider set of mainstream media users, illustrated by the intesity of colour.

The map reveals the networks of the many smaller groups of users who share more narrow interests. This picture provides evidence that the Leave campaign is a more tightly knit group with less diverse sub groups than the Remain campaign.

The People
In the list of the top 10 people with overall support are some familiar names:

There are three influential names here that prove to be most intriguing: Polly Toynbee, Katie Hopkins and Alison Pearson.

Here, we can ask the question: why were these three powerful women influential in the Brexit debate this week?
Without any prior knowledge of these women’s political persuasion or position on Brexit, we can see that, when identified on our network map, these women have differing view on the debate.

We noticed something quite interesting about how the three women achieved their influence. For this we looked at their networks, which shows all the other users in the network that are just one jump away from them, also known as an Ego Network.

Polly Toynbee
This is a small network with one other influential user in the network – “The Guardian”, which has 5m followers. The influence of Polly Toynbee would seem to be inextricably linked to the Guardian Newspaper.

Katie Hopkins
This is a much bigger network. The second most visible user in this network is David Vance who has 20k followers. In Katie Hopkins’ case this look very much more like a popular following of ‘ordinary’ people.

Allison Pearson
This network is also quite big and has one other main user in it — Nigel Farage, who has 260k followers and is a key player in this debate. The conclusion you might draw from this is that Allison Pearson is an ally of Nigel Farage.

Everything is obvious, once you know the answer

Of course, all of these findings come as no surprise to those engaged in politics. For instance, the fact that Polly Toynbee is an influential journalist working for the Guardian does not seem like much of a revelation if you are familiar with the domain of UK political journalism.

However, this analysis illustrates how it is possible to discover insights into the influence of users on Twitter without any pre-existing knowledge. The analysis was done from a starting point of zero knowledge of the role of that these three women within the debate, with only machine learning and the discovered information displayed in the network maps and dashboard. This proves the power of the tools and how information can be uncovered about influencers, the stories they are swaying and, importantly, the context in which they are exerting their impact.

Whichever side of the debate you are on, the insight that can be gained about who is shaping the conversation is valuable information. For an expert analyst with a deeper knowledge of the UK Brexit campaigns, there are much deeper insights to be gained by using these techniques.

John Swain is an associate researcher at Demos and a specialist in data science social network and graph analysis at Right Relevance. He tweets @swainjo.