Dr Sam Power, Lecturer in Corruption Analysis in the Politics Department, University of Sussex
On what services is money spent at elections? This is primary question behind this project. We know that just over £50 million was spent at the last general election, but strikingly little about how. Parties have to report their spending to the Electoral Commission under broad categories (e.g. ‘advertising’ and ‘market research and canvassing’), but this provides very little detail. They do, however, have to provide invoices for any spend over £200 so there is a vast resource available to find out more.
To address this gap, I (with a research team) manually coded every invoice (6,396) that was submitted to the Electoral Commission by political parties at the 2019 general election – which allowed us to paint a better picture of overall spend. These findings were written up into a report, a blog, and covered in the national media. The challenge here might seem obvious. It took ages and was incredibly arduous. There is much more information, available from many other elections, that could be analysed. I think, quite simply, there must be a better way. And perhaps that is via machine learning.
What we have to facilitate this better way, is a fantastic training set. I have provided two excel spreadsheets which contain the spending from the coding exercise. They have the name of the party conducting the spend, the amount of spend and the category that said spend falls under (you can see the amount of money written in the category). The Electoral Commission ‘political finance database’ hosts all of the invoices.
The suppliers that political parties use at elections took on new prominence after the Cambridge Analytica Scandal. And concerns about the ways in which modern technology, particularly social media platforms, are changing elections – and more widely democracy itself – are front and centre in the minds of many of us that study politics. But without a clear understanding on just what money is spent on, we cannot make a reasonable judgement about whether these trends are damaging and, if they are, how to combat them.