Political Text Scaling Meets Computational Semantics

TL;DR

This paper introduces SemScale, a semantically aware text scaling algorithm that improves the capture of political dimensions in legislative speeches by integrating computational linguistics and graph-based clustering.

Contribution

The paper presents SemScale, a novel text scaling method that incorporates semantic representations, challenging the traditional frequency-based approaches in political text analysis.

Findings

Semantic document representations outperform frequency-based methods in capturing political dimensions.

SemScale provides more accurate scaling of political texts across multiple languages and legislative terms.

The authors release an open-source implementation and datasets for further research.

Abstract

During the last fifteen years, automatic text scaling has become one of the key tools of the Text as Data community in political science. Prominent text scaling algorithms, however, rely on the assumption that latent positions can be captured just by leveraging the information about word frequencies in documents under study. We challenge this traditional view and present a new, semantically aware text scaling algorithm, SemScale, which combines recent developments in the area of computational linguistics with unsupervised graph-based clustering. We conduct an extensive quantitative analysis over a collection of speeches from the European Parliament in five different languages and from two different legislative terms, and show that a scaling approach relying on semantic document representations is often better at capturing known underlying political dimensions than the established frequency-based (i.e., symbolic) scaling method. We further validate our findings through a series of experiments focused on text preprocessing and feature selection, document representation, scaling of party manifestos, and a supervised extension of our algorithm. To catalyze further research on this new branch of text scaling methods, we release a Python implementation of SemScale with all included data sets and evaluation procedures.