Can network science help us understand and possibly predict voting behavior on contentious political issues? In a recent article in Applied network science, Carla Intal and Taha Yasseri examined the voting behavior of British MPs in order to identify and analyze intra-party conflicts and inter-party alliances in the context of Brexit.

Brexit is by far one of the hottest topics from Britain in recent years. In 2016, the year the UK voted to leave the European Union in a referendum, “Brexit” was the most searched news event on Google in the UK (and number three worldwide).

The following year, 2017, the main “what is…” question the British asked Google was “What is a hanging parliament?” And in 2019 the keywords “Petition Rule 50 Revoked” and “What is a backstop” belonged to it the top search trends of the year.

MEPs almost always vote according to their party lines, except on questions of European integration

Like many other political issues, Brexit has split people into opinion camps, but the difference between Brexit and other issues is that it split people across the political spectrum, which not only adds a bit too much extra heat to family gatherings, but also the otherwise orderly politics is challenging the UK in an unprecedented way.

The British party system is known for its discipline and cohesion, and MPs almost always vote according to their party lines, with the exception of issues relating to European integration.

In our study, we examined the challenges facing the British party system and developed a model that would even allow us to predict the unexpected votes of MPs against their party that would earn them the title “rebels”.

Using Hansard (the official archives of the UK Parliament) we analyzed the voting results of every MP in the 57th Parliament, the legislature immediately following the 2016 referendum.

For each pair of MPs, we quantified how similarly they voted on all parliamentary matters (also known as “divisions”). Note that MPs’ similarity scores could be negative if they tend to vote in opposite directions.

It will come as no surprise then if two Conservative MPs have a high resemblance score or if one Labor MP compares negatively to a Conservative MP. In fact, we see that on non-Brexit issues, a majority of MEPs voted according to this pattern.

It is surprising if two MPs from the same party show a high negative similarity value or if two MPs from an opposing party show a high similarity. This pattern was much more common when Brexit issues were discussed and voted on in parliament.

By comparing the similarity values ​​with what is “expected” purely on the basis of party affiliation, we have developed measures for “intra-party repulsion” and “cross-party attraction”.

You can view these two as “forces” that position MPs in the political arena. However, in order to determine the position of an MP, we need to calculate all the forces coming from all of the other MPs.

This is where network science comes into play. Even commercially available network visualization techniques lead to a very clear picture!

Network visualization of the top “rebel” MPs

© The authors

This graph shows the position of MPs in relation to the rest based on the “forces” that include repulsion within the parties and cross-party attraction. The most notable rebels are those positioned far from their party colleagues.

However, this goes beyond visualizations. Again, using the term “centrality” from network science, we have calculated a rebellion score for each MP based on any similarities and dissimilarities they show with other MPs.

asterisk

indicate that the MP was also identified by the network visualization.

As you can see in the table, the top rebels are the same MPs identified through the visual inspection of the network.

Our model has been used so far to understand who is not following your party, but could we have used it to make predictions about how MEPs will vote in the future?

In other words, if UK Prime Minister Boris Johnson had known a bit of network science, could he have foreseen what was to come in the historic October 22nd 2019 vote when MPs rejected his Brexit bill schedule?

We did the math and forecast how each MP would vote on this deal and whether they would rebel against their party expectations based on data collected just months before the day.

Our method could separate rebels from non-rebels with an amazing accuracy of over 90%!

Here we learn two things: first, nothing in recent British politics has blurred party lines like Brexit; and second, while it may sound confusing and inconceivable, network science can help us not only understand it, but even predict it!

Parliamentary debates, votes and actions in general have been recorded for centuries, but it is only recently that we have developed the tools to analyze the behavior and interactions of MPs on a large scale in almost real time. This could be the beginning of a new data-driven policy.

LEAVE A REPLY

Please enter your comment!
Please enter your name here