Journal of Political Institutions and Political Economy > Vol 6 > Issue 3–4

Towards Qualitative Measurement at Scale: A Prompt-Engineering Framework for Large-Scale Analysis of Deliberative Quality in Parliamentary Debates

Mitchell Bosley, Postdoctoral Researcher, Centro Nacional de Investigación en Inteligencia Artifical (CENIA), Chile, mitchellbosley@gmail.com
 
Suggested Citation
Mitchell Bosley (2025), "Towards Qualitative Measurement at Scale: A Prompt-Engineering Framework for Large-Scale Analysis of Deliberative Quality in Parliamentary Debates", Journal of Political Institutions and Political Economy: Vol. 6: No. 3–4, pp 355-383. http://dx.doi.org/10.1561/113.00000128

Publication Date: 01 Oct 2025
© 2025 M. Bosley
 
Subjects
Congress,  Government,  Legislatures,  Parliamentary politics,  Political participation,  Natural language processing for IR,  Question answering,  Summarization,  Text mining,  Data mining,  Deep learning
 
Keywords
Discourse analysislarge language modelsartificial intelligenceCongress
 

Share

Download article
In this article:
Introduction 
Previous Work 
Methodology 
Results 
Discussion 
Conclusion 
References 

Abstract

This paper investigates whether Large Language Models (LLMs), guided by prompt engineering, can automate the complex Discourse Quality Index (DQI) for measuring deliberative quality. Evaluating state-of-the-art models from OpenAI and Google by varying In-Context Learning (ICL) examples (0–50) shows LLMs achieve high fidelity, comparable to human annotators based on standard reliability metrics. Performance improves markedly with few examples, plateauing around 25–50 examples. While both models perform well, differences highlight the interplay between model selection and ICL strategy. Error analysis identifies specific DQI dimensions requiring further improvement, suggesting future work on advanced reasoning prompts. This study confirms LLM viability for scaling DQI measurement and provides practical guidance on optimizing ICL strategies. Additionally, it contributes a modular, adaptable AI engineering pipeline that researchers can leverage for their own prompting experiments across various measurement tasks.

DOI:10.1561/113.00000128

Online Appendix | 113.00000128_app.pdf

This is the article's accompanying appendix.

DOI: 10.1561/113.00000128_app

Companion

Journal of Political Institutions and Political Economy, Volume 6, Issue 3-4 Special Issue: Artificial Intelligence and the Study of Political Institutions
See the other articles that are part of this special issue.