Text and Policy Research Group
The Text and Policy 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 methods to address substantive questions and provide policy recommendations. Our current projects focus on legislative politics, political communication, higher education policy, climate and energy policies, 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
Stefan Müller (Group Leader)
Associate Professor
Sarah King
PhD Researcher
Funding: UCD Iseult Honohan Doctoral Scholarship
Mafalda Zúquete
PhD Researcher
Funding: PhD Studentship, Portuguese Foundation for Science and Technology
Former Team Members
Brian Boyle
Lecturer with tenure at Newcastle University
Previously Postdoctoral Researcher in NexSys Project
Alberto de León
Postdoctoral Researcher at Universidad Carlos III de Madrid
Previously Postdoctoral Researcher in Project funded by the Swiss National Science Foundation
Yen-Chieh Liao
Research Fellow at the University of Birmingham
Previously Postdoctoral Researcher in NexSys Project
Jihed Ncib
Postdoctoral Researcher at University College Dublin, School of Computer Science
Previously Ad Astra PhD Scholar
Robin Rauner
Policy Analyst at EirGrid
Previously Research Scientist in NexSys Project
Publications
Below, you find a selection of recent publications. For a full list of publications, please visit the team members’ individual websites.
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 online first.PDF | Classifiers | Code | Data Management Plan
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.
PDF | Data and Code
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.
PDF | Data and Code
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.
PDF | Data and Code
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.
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.
PDF | Data and Code | Summary
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.
PDF | Data and Code
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.
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.
PDF | Data and Code | PolNos Datasets | The Conversation
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.
PDF | Data and Code
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.
PDF | Data and Code | ECPR The Loop
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.
Research Projects
Assessing and Explaining Environmental and Energy Policies in Comparative Perspective
Researchers: Stefan Müller, Brian Boyle, Yen-Chieh Liao, and Robin Rauner
Project Summary: 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.
Funding: Next Generation Energy Systems (NexSys)
Publications:
- 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
Project Summary: 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.
Funding: Swiss National Science Foundation
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 online first.
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 (PDF) | Classifiers | Code | Data Management Plan