Data, machine learning, and AI for research on politics, public opinion, and evidence-based policy.
The Politics and Data Research Group comprises researchers from Germany, Portugal, Spain, Taiwan, Tunisia, the United Kingdom, and the United States. All members are based or have previously worked in the School of Politics and International Relations at University College Dublin.
The research group applies computational text analysis, machine learning, and large language models to address substantive questions and provide policy recommendations. Our current projects focus on legislative politics, political communication, public opinion, higher education policy, climate and energy policies, artificial intelligence and democracy, and “research on research”. The Handbook (PDF) contains our values, advice, and best practices.
We provide consultancy services to organisations in both the private and public sectors through ConsultUCD. Our consultancy services can be customised to meet your specific needs. Please get in touch if you have any questions.
Meet the Team
Current Members
Former Members
University College Dublin
Publications
Below, you find a selection of recent publications. For a full list of publications, please visit the team members’ personal websites.
2026
Yen-Chieh Liao and Li Tang. “Electoral Systems and Geographically Targeted Oversight: Evidence from the Taiwan Legislative Yuan.” Electoral Studies 99: 103026.
Abstract
Electoral systems have profound effects on legislator-constituent communication and representation. In this paper, we examine how Taiwan’s electoral reform, from multi-member districts under the Single Non-Transferable Vote (SNTV) to single-member districts under a Mixed Member Majoritarian system (MMM), shapes district legislators’ particularistic behaviour. Using fine-tuned transformer architectures, we analyse over 63,000 parliamentary questions from 402 district legislators spanning two decades to identify geographically targeted content. Controlling for legislator and municipal characteristics, we find that the reform from SNTV to MMM reduces geographically targeted questions, though this effect varies across municipalities with different economic profiles. Our analysis reveals that SNTV is associated with greater particularistic responsiveness to local socioeconomic conditions than single-member districts under MMM, suggesting that candidate-centred electoral systems of different types produce different behavioural incentives.
2026
Sebastian Stier, Sebastian A. Popa, Yannis Theocharis, and Brian Boyle. “Online Election Campaigning in Changing Political Environments: A Comparison of the 2014 and 2019 European Parliament Elections.” Party Politics 32(1): 115–126.
Abstract
It has long been assumed that social media would equalize election campaigning by providing cheap means of communication for smaller parties who lack a strong mass media presence. Yet given the increased political importance of social media, parties with more professional staff and resources could also gain the upper hand in online campaigns. So far, knowledge of the development of online campaigning in a rapidly changing political and technological landscape remains limited, as only few studies have taken a longitudinal and cross-country approach so far. This paper conducts a comprehensive analysis of more than 12,000 unique candidates from all 28 European Union (EU) member states in the 2014 and 2019 European Parliament (EP) elections. We theorize and empirically assess how party size and parties’ EU position relate to the presence, the activity and the salience of the EU among EP candidates on Twitter (now X). In the 2019 election, parties with a bigger national vote share and Europhile parties were more likely to be present and use Twitter more frequently to tweet about the EU. Overall, the findings point to a “normalization” of online election campaigning and a further convergence of first and second-order elections.
2026
Robin Rauner. “Greenwashing the Future? Computational Text Analysis of Environmental Reporting From the Fossil Fuel Industry.” Climate Policy, 1–16.
Abstract
Achieving net zero greenhouse gas emissions by mid-century is central to climate policy agendas worldwide. As pressure mounts to show progress towards the energy transition, an increasing number of companies are committing to climate targets and risk engaging in ‘futurewashing’, a new form of misleading communication practice. Pairing the Net Zero Tracker dataset with a novel text corpus, this research uses computational methods to analyze forward-looking discourse in the sustainability reports of 97 fossil fuel companies on the Forbes Global 2000 list. After assessing climate target characteristics, a conventional keyword-based and more sophisticated large language model (LLM) approach are compared to capture future focus. This demonstrates that implementing a dynamic few-shot prompt with Meta’s Llama 3.1 405B model outperforms a custom-made dictionary classifier. Using the LLM, the prevalence of forward-looking statements is identified to measure future focus. This analysis finds that while future focus tends to be higher for companies with stronger climate targets, the prevalence of forward-looking statements varies greatly across the fossil fuel industry and suggests inconsistent messaging at the company level. Amid the proliferation of climate targets and the development of mandatory requirements for sustainability reporting, quantitative text analysis of corporate climate communication can contribute to an emerging understanding of ‘futurewashing’ and provide empirical insights to inform policy practitioners.
2025
Gabriel Okasa, Alberto de León, Michaela Strinzel, Anne Jorstad, Katrin Milzow, Matthias Egger, and Stefan Müller. “A Supervised Machine Learning Approach for Assessing Grant Peer Review Reports.” Quantitative Science Studies 6: 1189–1214.
Abstract
Peer review is essential to the research lifecycle, yet the contents of grant peer review reports remain underexplored. Our study addresses this gap by developing a pipeline to systematically analyze these reports using Natural Language Processing and Machine Learning. We define twelve categories relevant to funding agencies, create an annotation codebook, fine-tune and validate transformer models, and apply these classifiers to a novel text corpus consisting of 1.6 million sentences from 47,522 grant peer review reports submitted to the Swiss National Science Foundation. This work has critical implications for the academic community. It provides novel insights into the content of grant peer review reports and openly available tools to enhance transparency, fairness, and consistency in grant evaluation. Our findings also highlight differences between journal and grant peer reviews, while the developed framework enables funding agencies and researchers to refine practices, fostering a more trustworthy and efficient evaluation process.
2025
Brian Boyle, Yen-Chieh Liao, Sarah King, Robin Rauner, and Stefan Müller. “Catalysts for Progress? Mapping Policy Insights From Energy Research.” Energy Research & Social Science 121: 103955.
Abstract
This article measures policy relevance in the abstracts of papers published between 2010 and 2023 in the top 100 journals covering energy research. Communicating the impact of research beyond academia is key to overcoming the evidence-policy divide. Yet, policy engagement is shaped by structural factors and poses unresolved dilemmas for researchers. Qualitative analyses of how research findings are presented in publications are inherently limited in scope, while simple search queries miss contributions that do not refer to ‘policy’ explicitly. Undertaking a large-scale bibliometric analysis, we use computational methods to evaluate over 270,000 abstracts by applying a carefully validated keyword-based dictionary approach. Overall, we find that 15 % of abstracts contain policy-relevant statements, with considerable differences among journals mentioning policy in their aims and scope. We also observe geographic variation by authorship and the funding agencies that sponsored research projects. Finally, we apply unsupervised topic models to identify distinct themes in policy-relevant abstracts. Our analysis reveals that the topics of renewable energy and implementation are most prevalent but have declined since 2010, while the focus on energy systems and emissions has gradually increased. These findings inform ongoing discussions about bridging the gap between research and policy impact in a field that will play a pivotal role in developing pathways to net zero.
2025
Yen-Chieh Liao. “Electoral Reform and Fragmented Polarization: New Evidence from Taiwan Legislative Roll Calls.” Legislative Studies Quarterly 50(1): 3–21.
Abstract
This paper investigates how legislators respond to an electoral reform by adjusting their positions with respect to co-partisans and rivals. Using cross-sectional legislative roll calls over 20 years, we study how the dynamics of blue-green confrontation are influenced by Taiwan’s electoral reform from Single Non-Transferable Votes (the SNTV) to Single-Member Districts (SMD). Contrary to existing literature, our empirical evidence shows that the reform significantly fragmented legislator positions within their party and in relation to members from opposing parties, leading to an increase in contentious legislation and higher levels of both inter- and intra-party distance. In the years following the reform, the political confrontation between the Kuomintang and the Democratic Progressive Party gradually diminished, eventually returning to levels seen before the reform. Moreover, our analysis reveals that the 2008 reform had heterogeneous effects on different parties, with each party displaying varying levels of resilience in response. This finding contributes to electoral system literature, providing policy implications for democratic countries contemplating electoral reforms.
2025
James P. Cross, Derek Greene, Stefan Müller, and Martijn Schoonvelde. “Mapping Digital Campaign Strategies: How Political Candidates Use Social Media to Communicate Constituency Connection and Policy Stance.” Computational Communication Research 7(1): 1–32.
Abstract
Social media have become a crucial tool for candidates seeking election, allowing them to build a public profile by posting curated content to appeal to potential voters. Focusing on the 2020 Irish General Election, this study investigates how candidates used Twitter to signal their campaign efforts and policy positions, and how their communicative priorities varied based on their gender, competitiveness, and political experience. To do so, we first demonstrate that a transformer-based machine-learning approach based on sentence embeddings can successfully identify social media posts that contain policy and electioneering content. Our findings show that experienced candidates are more likely to emphasise policy-related content than less experienced ones. This pattern also holds for electioneering content when we account for previous engagement with such posts. Contrary to our pre-registered expectations, we find no meaningful differences in the emphasis on electioneering or policy content based on candidates’ gender or electoral competitiveness. Overall, our results demonstrate how candidates strategically use social media to shape their public personas during election campaigns in Ireland’s candidate-centred electoral system, with multi-member constituencies and strict campaign spending limits.
2025
Stefan Müller and Naofumi Fujimura. “Campaign Communication and Legislative Leadership.” Political Science Research and Methods 13(3): 545–566.
Abstract
Do policy priorities that candidates emphasize during election campaigns predict their subsequent legislative activities? We study this question by assembling novel data on legislative leadership posts held by Japanese politicians and using a fine-tuned transformer-based machine learning model to classify policy areas in over 46,900 statements from 1270 candidate manifestos across five elections. We find that a higher emphasis on a policy issue increases the probability of securing a legislative post in the same area. This relationship remains consistent across multiple elections and persists even when accounting for candidates’ previous legislative leadership roles. We also discover greater congruence in distributive policy areas. Our findings indicate that campaigns provide meaningful signals of policy priorities.
2025
Royce Carroll, Yen-Chieh Liao, and Li Tang. “(Mis)perception of Party-voter Congruence and Satisfaction with Democracy.” Political Science Research and Methods 13(4): 885–902.
Abstract
This study examines how voters’ perceptions of ideological incongruence with political parties affect their satisfaction with democracy. Using panel data from the British Election Study, we first demonstrate that greater misperception of party positions correlates with higher perceived ideological distance from one’s preferred party. We then show that this increased perceived incongruence is associated with lower satisfaction with democracy when controlling for objective measures of incongruence. These findings are consistent across several alternative measures and specifications, and similar results are found in cross-sectional data from Europe. The results suggest that subjective perceptions of representation, potentially distorted by misperceptions, play a role in shaping citizens’ attitudes toward the political system. While the limitations of the study warrant caution in interpretation, the study contributes to the literature by highlighting the importance of perceived ideological congruence for understanding the link between representation and satisfaction with democracy.
2025
Heinz Brandenburg, Brian Boyle, and Yulia Lemesheva. “Brexit and the Iraq War on BBC Question Time: Demographic and Political Issue Representation in UK Public Participation Broadcasting.” The International Journal of Press/Politics 30(4): 980–1000.
Abstract
Public broadcasters are bound by strict guidelines to ensure balance in representing different demographic and political groups, and to better reflect the distribution of these characteristics within the public and political elites. How are these decisions affected when the biggest political issues of the day create further cleavages that not only cross-cut existing divides but also deserve representation in political discourse? In this article, we examine how panel selection on BBC Question Time dealt with this in relation to two prominent issues in twenty-first century UK politics: Brexit and the UK invasion of Iraq. We introduce an original dataset including all BBC Question Time appearances between 2001 and 2019, created using a combination of web-scraping and expert coding. This allows us to trace patterns in representation across sex, ethnicity, educational background, as well as partisan affiliation and stances on issues like Brexit and the Iraq war among the show’s panelists. We find that panel selection closely reflects gender and ethnic diversity among the UK public and MPs, but that individuals from privileged educational backgrounds are vastly overrepresented on the show. For both the Iraq war and Brexit, the show again broadly reflects the views of the public and political elites once we account for relevant comparisons between politicians and non-political guests.
2024
Stefan Müller and Sven-Oliver Proksch. “Nostalgia in European Party Politics: A Text-Based Measurement Approach.” British Journal of Political Science 54(3): 993–1005.
Abstract
Traditional research on political parties pays little attention to the temporal focus of communication. It usually concentrates on promises, issue attention, and policy positions. This lack of scholarly attention is surprising, given that voters respond to nostalgic rhetoric and may even adjust issue positions when policy is framed in nostalgic terms. This article presents a novel dataset, PolNos, which contains six text-based measures of nostalgic rhetoric in 1,648 party manifestos across 24 European democracies from 1946 to 2018. The measures combine dictionaries, word embeddings, sentiment approaches, and supervised machine learning. Our analysis yields a consistent result: nostalgia is most prevalent in manifestos of culturally conservative parties, notably Christian democratic, nationalist, and radical right parties. However, substantial variation remains regarding regional differences and whether nostalgia concerns the economy or culture. We discuss the implications and use of our dataset for studying political parties, party competition, and elections.
2024
Stefan Müller and Jihed Ncib. “Legislating Landlords: Private Interests, Issue Emphasis, and Policy Positions.” Legislative Studies Quarterly 49(4): 925–942.
Abstract
Do private interests predict politicians’ rhetoric? Focusing on housing policy, we compare issue emphasis and positions of landlord politicians and politicians who do not own multiple properties. Ireland provides a unique opportunity to study legislating landlords’ behavior as housing has become one of the most important political issues. We construct a novel dataset of politicians’ homeownership status between 2013 and 2022, a period characterized by rising rent and property prices. We fine-tune a transformer-based machine learning model and apply text scaling and sentiment analysis to identify issue salience and positions on housing in over 870,000 tweets and parliamentary questions. Contrary to our expectations, landlord politicians do not avoid the topic of housing nor take different positions. We also find that government status does not influence this relationship. The results imply that private financial interests do not influence rhetoric on housing policy.
2024
Stefan Müller, Samuel Brazys, and Alexander Dukalskis. “Discourse Wars and ‘Mask Diplomacy’: China’s Global Image Management in Times of Crisis.” Political Research Exchange 6(1): 2337632.
Abstract
To achieve foreign policy goals and boost prestige, states try to influence how foreign publics perceive them. Particularly during crises, the imperative to mitigate a negative image may see states mobilize resources to change the global narrative. This paper investigates whether China’s ‘mask diplomacy’ efforts influenced portrayals of the country in the early days of the Covid-19 pandemic. We validate and apply a semi-supervised scaling method to 1.5 million English statements in newspapers around the world mentioning China and Covid-19. Multi-period difference-in-differences models reveal that media tone improved significantly after mask diplomacy engagement. Using its Covid-19 White Paper to determine China’s preferred external narratives, we also find that a country’s domestic media reproduced key terms more after the country received PRC support.
2024
Brian Boyle. “Engineering Democracy: Electoral Rules and Turnout Inequality.” Political Studies 72(1): 177–199.
Abstract
The issue of unequal electoral turnout poses serious concerns for both the overall health of democratic politics, and the extent to which certain groups exert an unequal influence on the political process. This article explores the relationship between electoral rules such as compulsory voting, electoral system proportionality, and voter registration with voter inequality in terms of age, income and education. This is examined using cross-national survey data and cross-level interactions between electoral institutions and socio-demographic variables. The final dataset is based on waves 2 to 4 of the Comparative Study of Electoral Systems, and contains information on 133,000 individuals, within 45 countries, between 2001 and 2016. The results indicate that compulsory voting is associated with a significant reduction in turnout inequalities, while the effects of proportionality and voter registration are somewhat more mixed.
Research Projects
Assessing and Explaining Environmental and Energy Policies in Comparative Perspective
Researchers Stefan Müller, Brian Boyle, Yen-Chieh Liao, and Robin Rauner
Funding Next Generation Energy Systems (NexSys)
Political parties, politicians, companies, and interest groups increasingly discuss how to achieve a net-zero carbon emissions future, but systematic evidence that tracks these political debates is still lacking. The project seeks to identify the problems political actors raise and solutions they offer regarding renewable energy, sustainability, and water treatment. The project will also assess how companies and interest groups aim to reduce greenhouse gas emissions and help mitigate the impacts of climate change. By combining quantitative text analysis, human coding, and supervised machine learning, it will define and map (proposed) policies relating to the environment and sustainability, and provide recommendations for policymakers.
Publications
- Robin Rauner. 2026. “Greenwashing the Future? Computational Text Analysis of Environmental Reporting From the Fossil Fuel Industry.” Climate Policy, 1–16. PDF Data and Code
- Brian Boyle, Yen-Chieh Liao, Sarah King, Robin Rauner, and Stefan Müller. 2025. “Catalysts for Progress? Mapping Policy Insights From Energy Research.” Energy Research & Social Science 121: 103955. PDF Data and Code
Analysing Grant Peer Review Reports Using Machine Learning
Researchers Stefan Müller and Alberto de León
Funding Swiss National Science Foundation
Peer review plays an essential role in grant evaluation. External peer review reports by international experts contribute to assessing the feasibility and quality of grant applications and provide an essential basis for funding decisions. This research project analyses the texts of anonymised grant review reports along several dimensions using human coding and machine learning. We seek to conceptualise characteristics of grant peer review reports and classify a large corpus of review reports. The project investigates whether strategic initiatives and new evaluation procedures have the desired effects on the content and structure of review reports.
Publications
- Gabriel Okasa, Alberto de León, Michaela Strinzel, Anne Jorstad, Katrin Milzow, Matthias Egger, and Stefan Müller. 2025. “A Supervised Machine Learning Approach for Assessing Grant Peer Review Reports.” Quantitative Science Studies 6: 1189–1214. PDF Classifiers Code Data Management Plan
- Stefan Müller, Gabriel Okasa, Michaela Strinzel, Anne Jorstad, Katrin Milzow, and Matthias Egger. 2025. “Gender and Discipline Shape Length, Content and Tone of Grant Peer Review Reports.” arXiv preprint. Preprint Code
Associated Research Centres
Members of the group are involved in the following research centres and labs, as principal investigators, project researchers, and collaborators. Much of the work described under research projects is carried out with them.
