In this new blog post, my co-authors and I introduce a novel machine-learning approach to identifying important laws. We apply the new method to classify over 9,000 UK statutory instruments, and discuss the pros and cons of their approach.
Thousands of laws are published every year. In Britain, more than 300 public acts and almost 25,000 statutory instruments reached the statute book between 2010 and 2020. But which of these laws are really significant, and which ones are relatively minor? This is an important question for businesses and individuals. It is also one that many social scientists grapple with when studying law-making.
Read the full post at the LSE British Politics blog.
Radoslaw Zubek (2020) `Committee Strength in Parliamentary Democracies: A New Index’. European Journal of Political Research.
Much recent research on coalitions and policy-making in parliamentary democracies requires high quality data on the strength of legislative institutions. In this note, I introduce a new index of committee policing strength which improves on existing measures in important ways. I specify key index parameters using a binary rooted tree model and engage human coders to score formal rules. I obtain a novel time-series of committee policing strength in 17 western and eastern European democracies since 1945. I validate the new estimates through convergent validation and discuss ways in which the new index contributes to future work.
Radoslaw Zubek, Abhishek Dasgupta, David Doyle (2020) ‘Measuring the Significance of Policy Outputs with Positive Unlabeled Learning’. American Political Science Review. First View, 19 October 2020.
Identifying important policy outputs has long been of interest to political scientists. In this work, we propose a novel approach to the classification of policies. Instead of obtaining and aggregating expert evaluations of significance for a finite set of policy outputs, we use experts to identify a small set of significant outputs and then employ positive unlabeled (PU) learning to search for other similar examples in a large unlabeled set. We further propose to automate the first step by harvesting ‘seed’ sets of significant outputs from web data. We offer an application of the new approach by classifying over 9,000 government regulations in the United Kingdom. The obtained estimates are successfully validated against human experts, by forecasting web citations, and with a construct validity test.
I have been awarded a grant from the Research and Public Policy Partnership Scheme 2020 to support on-going collaboration between the ParlRulesData.org team, the House of Commons Library (HCL) and the Parliamentary Digital Service (PDS).
The ParlRulesData project digitilizes, analyzes and makes available historical, machine-readable records of parliamentary rules (“standing orders”, “rules of procedure”) through a dedicated data website, ParlRulesData.org (launched in July 2019). The HCL is an independent research and information unit, providing impartial information for UK Members of Parliament. The PDS is a specialized service supporting the House of Commons, the House of Lords and Parliament staff on their IT and digital needs.
Our collaboration project aims to bring significant benefits in terms of facilitating political transparency, public data access and democratic accountability. HC Standing Orders – the focus of our proposed partnership — govern the process by which parliament considers important elements of public policy – primary legislation, secondary legislation, and even treaties. Making good policy requires clarity and transparency about which parliamentary rules are applicable, how they should be complied with, and – in retrospect – whether they have been followed correctly.
Together with Tom Fleming and Niels Goet, I have written a post for the LSE British Politics and Policy Blog in which we introduce a machine‐readable dataset of House of Commons Standing Orders between 1811 and 2015. We demonstrate how our data can be used to measure procedural change, and thus substantially advance our understanding of legislative reforms. You can read the full post here.
Together with Thomas Fleming and Niels Goet, I have just launched ParlRulesData.org, an online database of parliamentary rules, containing the formal rules of procedure for various parliaments over time. The data currently covers the UK House of Commons (1811-2015) and the Irish Dáil (1926-2016).
Niels D. Goet, Thomas G. Fleming, Radoslaw Zubek (2019) ‘Procedural Change in the UK House of Commons, 1811-2015‘ Legislative Studies Quarterly. Online First.
Recent research has shown an increasing interest in the historical evolution of legislative institutions. The development of the United Kingdom Parliament has received particularly extensive attention. In this paper, we contribute to this liter- ature in three important ways. First, we introduce a complete, machine-readable dataset of all the Standing Orders of the UK House of Commons between 1811 and 2015. Second, we demonstrate how this dataset can be used to construct innovative measures of procedural change. Third, we illustrate a potential empir- ical application of the dataset, offering an exploratory test of several expectations drawn from recent theories of formal rule change in parliamentary democracies. We conclude that the new dataset has the potential to substantially advance our understanding of legislative reforms in the United Kingdom and beyond.
Together with Tom Fleming, I have written a post for OXPOL, the Oxford University Politics Blog, in which we argue that while the Brexit process may have challenged the UK government’s ability to control parliament, it was pushing at an open door. Recent events can thus be understood as an acceleration of pre-existing trends in Britain’s political institutions and political parties. You can read the full post here.
I have written a short piece for an online weekly, Kultura Liberalna, showing that, since the last Polish elections in 2015, the largest opposition party, the Civic Platform, has supported the PiS-led majority on almost 60% of all final passage votes. This evidence places a question mark over the claim that the PO provides an aggressive opposition to the PiS government. You can read the full article here (in Polish) and the raw data is available here.