Lorcan McLaren
PhD Researcher
University College Dublin
I am a PhD researcher in computational social science at University College Dublin, funded by a Taighde Éireann - Research Ireland Government of Ireland scholarship. Based in the Connected_Politics Lab under the supervision of James P. Cross, my research employs text-as-data approaches to examine political communication, with a particular focus on the climate crisis. Previously, I was supported by the Iseult Honohan scholarship and served as a Climate Fellow at the UCD Earth Institute.
Prior to my doctoral studies, I completed a BA in Computer Science, Linguistics and French at Trinity College Dublin and an MSc in Politics and Data Science at University College Dublin, complemented by two years of industry experience as a data analyst.
Research
Working Papers
Abstract
Climate change is increasing the frequency and severity of natural disasters. While extreme weather events may heighten public awareness of environmental changes, their influence on political rhetoric remains understudied. This paper examines whether natural disaster incidence shapes how Members of the European Parliament (MEPs) discuss climate change, with particular attention to the sense of proximity or distance from climate impacts created by their speech—whether climate change is presented as spatially and temporally urgent or as a distant problem, to be dealt with by faraway people or future generations.
While prior research shows that natural disasters do not increase environmental issue salience in party press releases, their impact on parliamentary speech remains unexplored. Moreover, disasters may alter qualitative aspects of climate discourse even without increasing its frequency.
Analysing European Parliament debates from 2014-2024 using large language models (LLMs), this study investigates how disaster incidence affects climate rhetoric, examining whether disaster characteristics—including proximity, type, number of people affected, and cost of damage—shape MEPs' representation of the climate crisis.
Abstract
Generative large language models (LLMs) have been embraced by the research community as a low-cost, quick, and consistent way to classify textual data. Prior scholarship has demonstrated the accuracy of LLMs across a variety of social science classification tasks. However, there has been little systematic investigation of the effect of model choice. model size, prompt style and hyperparameter settings on classification performance. This paper evaluates the importance of these choices across four distinct annotation tasks from the field of political science, using human-annotated texts as a benchmark. Our findings reveal significant tradeoffs between annotation performance and computational efficiency, with larger models and more complex prompts yielding inconsistent performance gains while substantially increasing inference time, energy consumption, and carbon emissions. Contrary to widely-held assumptions, popular prompt engineering techniques such as persona and chain-of-thought prompting demonstrate highly task- and model-dependent effects, sometimes degrading rather than improving performance. We also find that model size does not consistently correlate with better outcomes. These results underscore the necessity of task-specific empirical validation rather than universal best practices when designing LLM-based annotation workflows.
Abstract
Climate change represents an existential risk to global society, yet public engagement has not fully risen to meet the challenge. Political speech can change citizens' support for climate action and willingness to modify their behaviour. One feature that matters – including when speaking to oppositional audiences about climate – is psychological distance: the sense of proximity or distance from the impacts of climate change created by the speech. While extensive research demonstrates its importance for persuasion, it is unclear whether politicians employ this feature strategically. This paper addresses that gap by developing and validating automated methods to measure psychological distance in political speech. I introduce a translated dataset of 35,000 European Parliament speeches on climate-related topics (2014-2024). I explore and validate the use of generative language models to label training data for fine-tuning encoder classifiers, in order to identify this feature. Subsequent analysis sheds light on the internal and external motivators of climate communication, including the demographic characteristics of legislators and their ideological positions. Future avenues for research on the drivers of European climate politics are discussed, as are the implications for communication practitioners.
Publications
Proceedings of the 11th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), 2020.
Paper | Open Access | Code
Proceedings of the 11th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), 2020.
Paper | Open Access
Projects
Teaching
Module Instructor
- AI and Large Language Models, Postgraduate (Spring 2025, 2026) — Course Website | Syllabus
Teaching Assistant
- Introduction to EU Politics, Undergraduate (Autumn 2023, 2024)
- Research Methods in Political Science, Undergraduate (Spring 2024)
Contact
For inquiries, collaboration opportunities, or to discuss my work, feel free to reach out via email.