Political scientists can rely on a long tradition of applying unsupervised measurement models to estimate ideology and preferences from texts. However, in practice the hope that the dominant source of variation in their data is the quantity of interest is often not realized. In this paper, I argue that in the messy world of speeches we have to rely on supervised approaches that include information on party affiliation in order to produce meaningful estimates of polarization. To substantiate this argument, I introduce a validation framework that may be used to comparatively assess supervised and unsupervised methods, and estimate polarization on the basis of 6.2 million records of parliamentary speeches from the UK House of Commons over the period 1811–2015. Beyond introducing several important adjustments to existing estimation approaches, the paper’s methodological contribution therefore consists of outlining the challenges of applying unsupervised estimation techniques to speech data, and arguing in detail why we should instead rely on supervised methods to measure polarization.

The historical development of rules of debate in the UK House of Commons raises an important puzzle: why do members of parliament (MPs) impose limits on their own rights? Despite a growing interest in British Political Development and the institutional changes of nineteenth-century UK politics, the academic literature has remained largely silent on this topic. Three competing explanations have emerged in studies of the US Congress, focusing on efficiency, partisan forces and non-partisan (or: ideology-based) accounts. This article falls broadly into the third category, offering a consensus-oriented explanation of the historical development of parliamentary rules. Working from a new dataset on the reform of standing orders in the House of Commons over a 205-year period (1811–2015), as well as records of over six million speeches, the author argues that MPs commit more quickly to passing restrictive rules in the face of obstruction when legislator preferences are proximate within both the opposition and government, and when polarization between both sides of the aisle is low. The research represents, to the author's knowledge, the first systematic and directional test of a range of competing theories of UK parliamentary reform, shedding light on the process of parliamentary reform over a prolonged period of Commons history, and advancing several new measures of polarization in the UK House of Commons.

Recent research has shown an increasing interest in the historical evolution of legislative institutions. The development of the UK Parliament has received particularly extensive attention. In this article, we contribute to this literature in three important ways. First, we introduce a complete, machine‐readable data set of all the Standing Orders of the UK House of Commons between 1811 and 2015. Second, we demonstrate how this data set can be used to construct innovative measures of procedural change. Third, we illustrate a potential empirical application of the data set, offering an exploratory test of several expectations drawn from recent theories of formal rule change in parliamentary democracies. We conclude that the new data set has the potential to substantially advance our understanding of legislative reforms in the United Kingdom and beyond.

How and why do the activities of members of parliament (MPs) change in response to electoral constraints? In this article, we draw on unique and newly collected data from the Swiss federal chambers and two cantonal parliaments (Basel‐Stadt and Basel‐Land) to explore the effects of electoral constraints. Leveraging variation in mandatory term limits, we study the extent to which term‐limited MPs engage in shirking—that is, move away from their principal, whether it be the party and/or voters—and slacking—that is, reduce their parliamentary activities. Our analysis, which draws on a combination of novel roll‐call votes and speech data, yields mixed results: while there is no evidence of shirking by term‐limited MPs in the cantonal parliaments, we find some indications of such behavior among term‐limited legislators in the federal chambers. These latter legislators also engage in some limited slacking, which is not observable in the cantonal parliaments. Our findings shed light on the (political) implications of term limits and the effect of electoral constraints on legislator behavior.

Reliably answering questions about representation and parliamentary behavior requires data about which parliamentarian was where, and at what time. However, parliament membership is not stable over time. For example, it is common for politicians to change office (we find up to 40% turnover between elections). Consequently, parliament membership, as well as party and party group composition change on a daily basis. To address the challenges that these fluctuations present, we introduce a new open‐source database:‘ ‘Parliaments Day‐By‐Day” (PDBD). PDBD currently contains demographic and day‐by‐day membership data for the national parliaments of Germany, Switzerland, and the Netherlands, covering the period between 1947 and 2017, and comprising a total of 21 million parliament‐legislator‐day observations. We demonstrate the usefulness of this high‐resolution data in a concise study of the day‐by‐day development of parliaments in terms of gender and seniority. This reveals hitherto unknown patterns of early turnover, gendered replacement, and seniority.