Parlasent: mapping sentiment in political discourse with large language models

This paper introduces ParlaSent, a deep learning model for multilingual sentiment analysis, specifically designed to study sentiment in political discourse. Built upon the XLM-R-parla model – a domain-specific multilingual transformer based on XLM-RoBERTa – ParlaSent benefits from additional pre-tra...

Full description

Bibliographic Details
Published in:Political Research Exchange
Main Authors: Michal Mochtak, Peter Rupnik, Taja Kuzman, Nikola Ljubešić
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Subjects:
Sentiment
sentiment analysis
language model
Europe
Online Access:https://www.tandfonline.com/doi/10.1080/2474736X.2025.2508377

Internet

https://www.tandfonline.com/doi/10.1080/2474736X.2025.2508377

Similar Items