Topic modelling discourse dynamics in historical newspapers

TL;DR

This study applies LDA and DTM topic models to Finnish historical newspapers from 1854-1917 to analyze discourse changes over time, offering methodological innovations for large diachronic datasets.

Contribution

It introduces a combined sampling and inference procedure for large diachronic text collections and compares two topic models for discourse analysis.

Findings

Effective application of topic models to large, imbalanced historical newspaper data

Quantification of topic prominence over time

Insights into discourse dynamics in Finnish history

Abstract

This paper addresses methodological issues in diachronic data analysis for historical research. We apply two families of topic models (LDA and DTM) on a relatively large set of historical newspapers, with the aim of capturing and understanding discourse dynamics. Our case study focuses on newspapers and periodicals published in Finland between 1854 and 1917, but our method can easily be transposed to any diachronic data. Our main contributions are a) a combined sampling, training and inference procedure for applying topic models to huge and imbalanced diachronic text collections; b) a discussion on the differences between two topic models for this type of data; c) quantifying topic prominence for a period and thus a generalization of document-wise topic assignment to a discourse level; and d) a discussion of the role of humanistic interpretation with regard to analysing discourse dynamics through topic models.