Multi-aspect Multilingual and Cross-lingual Parliamentary Speech Analysis

TL;DR

This paper applies advanced NLP techniques to analyze parliamentary speeches across six countries, revealing commonalities and differences in emotions, sentiment, and speaker attributes from 2017 to 2020.

Contribution

It presents a comparative, multi-aspect NLP analysis of parliamentary debates across six nations, focusing on emotions, sentiment, and speaker attributes.

Findings

Identified cross-country similarities and differences in speech emotions and sentiment.

Demonstrated the feasibility of detecting speaker age, gender, and political orientation from speeches.

Provided insights into parliamentary discourse patterns across diverse political contexts.

Abstract

Parliamentary and legislative debate transcripts provide informative insight into elected politicians' opinions, positions, and policy preferences. They are interesting for political and social sciences as well as linguistics and natural language processing (NLP) research. While existing research studied individual parliaments, we apply advanced NLP methods to a joint and comparative analysis of six national parliaments (Bulgarian, Czech, French, Slovene, Spanish, and United Kingdom) between 2017 and 2020. We analyze emotions and sentiment in the transcripts from the ParlaMint dataset collection and assess if the age, gender, and political orientation of speakers can be detected from their speeches. The results show some commonalities and many surprising differences among the analyzed countries.