While many citizens support expanding direct democracy, its institutionalisation lags behind popular demand, presumably due to limited enthusiasm among political elites. This article explores both ideological and instrumental reasons why political parties support or avoid direct democracy. Using an original dataset of 701 election manifestos from German parties (1975–2017) and employing a custom dictionary and large language model, over 2,000 relevant statements were classified. Mentions of direct democracy are predominantly positive, as parties opposing it omit the topic, consistent with salience theory. Regression analyses reveal robust support among left-of-centre and populist parties. Moreover, challenger parties emphasise direct democracy more than mainstream parties, but maintain their stance when going mainstream. In contrast, parties are less likely to promote direct democracy when in government than when in opposition. These findings help explain the gap between citizen preferences and actual institutional reforms.

Businesses regularly cite the regulatory environment as an important consideration in production and hiring decisions, yet there is little research quantifying sentiment and uncertainty surrounding regulation. We present measures of sentiment and uncertainty about the U.S. regulatory environment using natural language processing applied to an original corpus of leading U.S. newspapers. We construct monthly indexes of regulatory sentiment and regulatory uncertainty, as well as categorical indexes for 14 regulatory policy areas, from 1985 through 2021. The estimated impulse responses suggest that a negative shock to regulatory sentiment is associated with large, persistent declines in future output and employment, whereas the responses associated with increased regulatory uncertainty are generally statistically insignificant or transitory. Economic outcomes are particularly sensitive to sentiment and uncertainty related to certain regulatory areas, including transportation, consumer safety and health, general business and trade, and energy regulation.

Political science increasingly uses text classification to gauge subtle concepts such as toxicity or anger. Traditional methods treat words in isolation, overlooking the contextual dynamics where meaning resides. Transformer-based language models address these limitations but remain underutilized, especially among applied scholars, partly due to misconceptions about their mechanisms and computational requirements. This article bridges this gap by offering an accessible explication of the pretrain-finetune paradigm, focusing on underlying mechanisms and their potential to improve political text analysis by harnessing models trained on extensive datasets while requiring modest labeled data and computational resources. I demonstrate the approach by identifying toxic language in conversation threads following U.S. Senators’ tweets and provide an online tutorial to support nontechnical scholars in adopting the methodology.

In Burundi, weekly services are the primary point of contact between churches and their followers, with most of the population attending. These gatherings provide churches with a strategic platform to attract and retain members. Over six months, we collected data from five churches in the rural town of Muramvya—Catholic, Anglican, Pentecostal, FECABU (Evangelical), and Adventist—analyzing 125 transcripts for structure, themes, scope, tone, and key words. We find that emerging denominations—Pentecostal, FECABU, and Adventist—pursue different strategies than traditional ones. Pentecostal and FECABU churches place greater emphasis on rituals than on scripture readings, adopt a more positive tone, and focus on the immediate concerns of their congregants rather than abstract topics. The Adventist Church, while also emphasizing rituals and using a positive tone, distinguishes itself with a stronger commitment to scripture. The Pentecostal church uniquely combines a focus on morality with references to supernatural punishment. We argue that this blend of approaches among emerging denominations strengthens group cohesion and enriches individual faith experiences, helping them attract followers. Our findings shed light on the growth of these denominations in Burundi and may help explain broader religious trends across Sub-Saharan Africa.

Text analysis typically focuses on content—such as sentiment or topic—but expression is also a form of effortful action. Building on this insight, I propose using simple features of open-ended tasks to study text as behavior. This approach treats expression, such as writing, as cognitively, emotionally and temporally “costly” for subjects but inexpensive for researchers. I show basic statistics like the number of characters can approximate effort and significantly improve estimation of quantities of interest, including candidate choice, the probability of turning out to vote and psychological states about which a subject may not be fully aware. Further, these methods can convert nonresponse into informative data; validate survey instruments; serve as mechanism checks; be hard for a subject to “game”; work across different languages and analogize well to real-world situations. In sum, text as behavior can help address a range of issues related to quantifying attitudes and actions.

State-registered religion is puzzling because it can be portrayed as both an opponent and a partner of the state. While registered religions need to be receptive to the rules of the government, they also need to satisfy the needs of their congregants. In light of the Communist Party’s increasing repression, I investigate how this complex positioning between the government and the congregation has influenced the content of sermons in state-approved Protestant churches. Using computational text analysis on sermons from a state-approved Protestant church in China between 2009 and 2021, I analyze the pastors’ degree and composition of self-censorship in their receptiveness to changes over time, as well as to politically and religiously sensitive dates. By focusing on sermons shared in state-approved churches, I shed light on the complex positions in which these Party-registered pastors maneuver. This research also contributes to the broader discussion of civil rights and state-society relations in the context of a strong authoritarian state.

In settings of deep poverty and inequality, implementing policies that balance urgent needs with long-term development is crucial. What strategies are used to build public support for long-term oriented policies? Evidence shows that both left- and right-wing governments have played a role in the expansion of social policy. This article explores the context and meanings that governments with different ideologies assign to distributive policies, focusing on how these policies are communicated. In particular, I argue that ideology significantly shapes the framing presidents use when discussing and announcing social policies. Left-leaning governments emphasize social inclusion while right-leaning governments stress the productivity-enhancing aspects of these policies. Using text analysis techniques, including à la carte embeddings (ALC) this study analyzes presidential communications from Argentina, Uruguay, and Chile. The findings show how ideology drives communication strategies, revealing that in more polarized societies, presidents distinguish themselves more consistently through how they construct and communicate these policies.

Research shows that increased participation of women in parliaments benefits climate change outcomes. Yet, the actions taken by women parliamentarians to shape these outcomes have not been identified in the literature. I assert that a primary step by which women may generate impact is by championing environmentalism in their speeches before parliament. To test this, I analyse speeches from the UK House of Commons from 2010 to 2021, and find that women MPs both speak proportionately more about the environment than their male counterparts, and bring environmentalism into debates that are not explicitly coded as environmental. Finally, while Conservative women are outnumbered by men, they contribute significantly more to environmental speeches than their male counterparts. These results suggest that women are disproportionately responsible for embedding environmentalism into political discussions across Parliament and the Conservative Party, and prompt questions around the true cost of unequal representation for our climate.

Efforts to curb online hate speech depend on our ability to reliably detect it at scale. Previous studies have highlighted the strong zero-shot classification performance of large language models (LLMs), offering a potential tool to efficiently identify harmful content. Yet for complex and ambivalent tasks like hate speech detection, pre-trained LLMs can be insufficient and carry systemic biases. Domain-specific models fine-tuned for the given task and empirical context could help address these issues, but, as we demonstrate, the quality of data used for fine-tuning decisively matters. In this study, we fine-tuned GPT-4o-mini using a unique corpus of online comments annotated by diverse groups of coders with varying annotation quality: research assistants, activists, two kinds of crowd workers, and citizen scientists. We find that only annotations from those groups of annotators that are better than zero-shot GPT-4o-mini in recognizing hate speech improve the classification performance of the fine-tuned LLM. Specifically, fine-tuning using the highest-quality annotator group – trained research assistants – boosts classification performance by increasing the model’s precision without notably sacrificing the good recall of zero-shot GPT-4o-mini. In contrast, lower-quality annotations do not improve and may even decrease the ability to identify hate speech. By examining tasks reliant on human judgment and context, we offer insights that go beyond hate speech detection.

An ever-increasing availability of digital texts has opened new research opportunities for political scientists. Yet, researchers who want to utilise these data face several challenges. This paper presents the results of a community-wide survey tapping into various research challenges, training needs, and preferences of scholars using text analysis methodologies. The survey involved respondents from various academic fields and career levels. Our findings indicate that text-as-data methods are gaining momentum in various political science subfields and are used on a wide range of political texts. However, relevant training is not easily accessible to all. Only half of the respondents have ever participated in a training event, though there is a high demand for training opportunities in different formats and at different levels. In ‘Conclusions’, we discuss how the inaccessibility of training risks narrowing the field of researchers.

A close connection between public opinion and policy is considered a vital element of democracy. However, legislators cannot be responsive to all voters at all times with regard to the policies the latter favour. We argue that legislators use their speaking time in parliament to offer compensatory speech to their constituents who might oppose how they voted on a policy, in order to re‐establish themselves as responsive to the public's wishes. Leveraging the case of Brexit, we show that legislators pay more attention to constituents who might be dissatisfied with how they voted. Furthermore, their use of rhetorical responsiveness is contingent on the magnitude of the representational deficit they face vis‐à‐vis their constituency. Our findings attest to the central role of parliamentary speech in maintaining responsiveness. They also demonstrate that communicative responsiveness can substitute for policy responsiveness.

Debates about the European Union's democratic legitimacy put national parliaments into the spotlight. Do they enhance democratic accountability by offering visible debates and electoral choice about multilevel governance? To support such accountability, saliency of EU affairs in the plenary ought to be responsive to developments in EU governance, has to be linked to decision‐making moments and should feature a balance between government and opposition. The recent literature discusses various partisan incentives that support or undermine these criteria, but analyses integrating these arguments are rare. This article provides a novel comparative perspective by studying the patterns of public EU emphasis in more than 2.5 million plenary speeches from the German Bundestag, the British House of Commons, the Dutch Tweede Kamer and the Spanish Congreso de los Diputados over a prolonged period from 1991 to 2015. It documents that parliamentary actors are by and large responsive to EU authority and its exercise where especially intergovernmental moments of decision making spark plenary EU salience. But the salience of EU issues is mainly driven by government parties, decreases in election time and is negatively related to public Euroscepticism. The article concludes that national parliaments have only partially succeeded in enhancing EU accountability and suffer from an opposition deficit in particular.

The promises and pitfalls of automated (computer-assisted) and human-coding content analysis techniques applied to political science research have been extensively discussed in the scholarship on party politics and legislative studies. This study presents a similar comparative analysis outlining the pay-offs and trade-offs of these two methods of content analysis applied to research on EU lobbying. The empirical focus is on estimating interest groups’ positions based on their formally submitted policy position documents in the context of EU policymaking. We identify the defining characteristics of these documents and argue that the choice for a method of content analysis should be informed by a concern for addressing the specificities of the research topic covered, of the research question asked and of the data sources employed. We discuss the key analytical assumptions and methodological requirements of automated and human-coding text analysis and the degree to which they match the identified text characteristics. We critically assess the most relevant methodological challenges research designs face when these requirements need to be complied with and how these challenges might affect measurement validity. We also compare the two approaches in terms of their reliability and resource intensity. The article concludes with recommendations and issues for future research.

From the early use of TF-IDF to the high-dimensional outputs of deep learning, vector space embeddings of text, at a scale ranging from token to document, are at the heart of all machine analysis and generation of text. In this article, we present the first large-scale comparison of a sampling of such techniques on a range of classification tasks on a large corpus of current literature drawn from the well-known Books3 data set. Specifically, we compare TF-IDF, Doc2vec and several Transformer-based embeddings on a variety of text-specific tasks. Using industry-standard BISAC codes as a proxy for genre, we compare embeddings in their ability to preserve information about genre. We further compare these embeddings in their ability to encode inter- and intra-book similarity. All of these comparisons take place at the book “chunk” (1,024 tokens) level. We find Transformer-based (“neural”) embeddings to be best, in the sense of their ability to respect genre and authorship, although almost all embedding techniques produce sensible constructions of a “literary landscape” as embodied by the Books3 corpus. These experiments suggest the possibility of using deep learning embeddings not only for advances in generative AI, but also a potential tool for book discovery and as an aid to various forms of more traditional comparative textual analysis.

Supervised learning is increasingly used in social science research to quantify abstract concepts in textual data. However, a review of recent studies reveals inconsistencies in reporting practices and validation standards. To address this issue, we propose a framework that systematically outlines the process of transforming text into a quantitative measure, emphasizing key reporting decisions at each stage. Clear and comprehensive validation is crucial, enabling readers to critically evaluate both the methodology and the resulting measure. To illustrate our framework, we develop and validate a measure assessing the tone of questions posed to nominees during U.S. Senate confirmation hearings. This study contributes to the growing literature advocating for transparency and rigor in applying machine learning methods within computational social sciences.

Servitization is a key strategy for enhancing competitiveness in manufacturing, yet the managerial drivers behind this transformation remain underexplored. This study investigates the impact of top executives’ service cognition on servitization using a novel index derived from text-mined disclosures of Chinese listed manufacturing firms (2007–2020). Results show that executives’ service cognition significantly promotes servitization, even after controlling for endogeneity using instrumental variables and Heckman’s two-stage model. Mechanism analysis reveals that this cognitive orientation enhances human capital accumulation and R&D investment, which in turn drive higher service levels. Furthermore, the relationship is moderated by executive power concentration and regional internet penetration. Heterogeneity tests indicate stronger effects in high-tech industries, state-owned enterprises, and large firms. These findings highlight the critical role of executive cognition in shaping strategic transformation and offer practical implications for firms and policymakers aiming to foster servitization through leadership development and supportive digital infrastructure.