Measuring the Unseen: A Statistical Approach to Quantifying Narrative Bias in Historical Accounts

An objective view of history is often treated as an ideal, yet historical narratives are inevitably shaped by the perspectives of their authors. I use word embeddings to examine the political leanings present in different historical accounts. I outline a framework for estimation and quantifying uncertainty. This project proposes a data-driven approach to representing historical narratives in a shared analytical space, enabling comparison across differing interpretive lenses.

Text embedding

Narrative decomposition

Natural Language Processing

Human–AI collaboration

Cosine distance

Generative AI 

AI and LLM Applications

Symposium on Data Science and Statistics (SDSS) 2026