Hierarchical Structured Model for Fine-to-coarse Manifesto Text Analysis

TL;DR

This paper introduces a hierarchical deep learning model that automatically analyzes election manifestos at both fine and coarse levels, improving accuracy across multiple countries and languages.

Contribution

A novel two-stage hierarchical structured model that jointly predicts fine- and coarse-grained political positions and calibrates results for better accuracy.

Findings

Outperforms state-of-the-art methods in manifesto analysis

Effective across twelve countries and ten languages

Enhances both fine- and coarse-grained political positioning accuracy

Abstract

Election manifestos document the intentions, motives, and views of political parties. They are often used for analysing a party's fine-grained position on a particular issue, as well as for coarse-grained positioning of a party on the left--right spectrum. In this paper we propose a two-stage model for automatically performing both levels of analysis over manifestos. In the first step we employ a hierarchical multi-task structured deep model to predict fine- and coarse-grained positions, and in the second step we perform post-hoc calibration of coarse-grained positions using probabilistic soft logic. We empirically show that the proposed model outperforms state-of-art approaches at both granularities using manifestos from twelve countries, written in ten different languages.