🤖 AI Summary
Political science has long lacked systematic identification and analysis of causal explanations in political texts; existing methods are fragmented, context-specific, and entail high annotation costs. Method: We propose the first structured causal relation detection framework tailored to political texts, integrating a lightweight causal language model with low-resource NLP techniques to enable high-precision, automatic extraction of cause-effect pairs from minimal annotated data. Contribution/Results: The framework achieves strong generalizability, near-human coding accuracy (F1 > 0.85), and cross-text robustness, validated across diverse political corpora—including news articles, policy commentaries, and legislative records. We release the first large-scale, structured dataset of political causal claims, substantially reducing manual coding effort. This work establishes a reproducible, scalable, and automated infrastructure for large-scale quantitative studies of causal attribution patterns in political discourse.
📝 Abstract
Explanations are a fundamental element of how people make sense of the political world. Citizens routinely ask and answer questions about why events happen, who is responsible, and what could or should be done differently. Yet despite their importance, explanations remain an underdeveloped object of systematic analysis in political science, and existing approaches are fragmented and often issue-specific. I introduce a framework for detecting and parsing explanations in political text. To do this, I train a lightweight causal language model that returns a structured data set of causal claims in the form of cause-effect pairs for downstream analysis. I demonstrate how causal explanations can be studied at scale, and show the method's modest annotation requirements, generalizability, and accuracy relative to human coding.