Comparative scholars of legislative politics continue to face the challenge of measuring a key theoretical concept: conflict at the level of legislative bills. We address this challenge with a multilingual sentiment-based approach and show that such a measure can effectively capture different types of parliamentary conflict. We also demonstrate that an automated translation of the dictionary yields valid results and therefore greatly facilitates comparative work on legislatures. Our applications show that a sentiment approach recovers government-opposition dynamics in various settings. the use of a simple, translatable sentiment dictionary opens up the possibility of studying legislative conflict in bill debates across languages and countries.

No abstract

The analysis of political texts from parliamentary speeches, party manifestos, social media, or press releases forms the basis of major and growing fields in political science, not least since advances in “text-as-data” methods have rendered the analysis of large text corpora straightforward. However, a lot of sources of political speech are not regularly transcribed, and their on-demand transcription by humans is prohibitively expensive for research purposes. This class includes political speech in certain legislatures, during political party conferences as well as television interviews and talk shows. We showcase how scholars can use automatic speech recognition systems to analyze such speech with quantitative text analysis models of the “bag-of-words” variety. To probe results for robustness to transcription error, we present an original “word error rate simulation” (WERSIM) procedure implemented in $R$. We demonstrate the potential of automatic speech recognition to address open questions in political science with two substantive applications and discuss its limitations and practical challenges.

What can policy makers do in day‐to‐day decision making to strengthen citizens' belief that the political system is legitimate? Much literature has highlighted that the realization of citizens' personal preferences in policy making is an important driver of legitimacy beliefs. We argue that citizens, in addition, also care about whether a policy represents the preferences of the majority of citizens, even if their personal preference diverges from the majority's. Using the case of the European Union (EU) as a system that has recurringly experienced crises of public legitimacy, we conduct a vignette survey experiment in which respondents assess the legitimacy of fictitious EU decisions that vary in how they were taken and whose preferences they represent. Results from original surveys conducted in the five largest EU countries show that the congruence of EU decisions not only with personal opinion but also with different forms of majority opinion significantly strengthens legitimacy beliefs. We also show that the most likely mechanism behind this finding is the application of a ‘consensus heuristic’, by which respondents use majority opinion as a cue to identify legitimate decisions. In contrast, procedural features such as the consultation of interest groups or the inclusiveness of decision making in the institutions have little effect on legitimacy beliefs. These findings suggest that policy makers can address legitimacy deficits by strengthening majority representation, which will have both egotropic and sociotropic effects.

As the share of women in parliaments rises, increased attention is paid to how they substantively represent women. Meanwhile, the availability of parliamentary speech data has enabled researchers to dissect politicians’ rhetorical patterns. We combine these two literatures to ask whether rhetorical differences between men and women in parliament are connected to style, policy, and preferences of women voters. We apply machine‐learning models to speeches from five West European parliaments (2000–18) to measure the femininity of the rhetoric used in each speech. Results show that women and men talk differently in parliament, and that this distinctiveness is due to both style and substance. Combining these results with public opinion surveys, we find that women MPs have the most distinctively “feminine” discourse on issues that are most salient to women in society. These findings showcase the direct connection between descriptive and substantive representation of women in contemporary democracies.