High risk of political bias in black box emotion inference models

Abstract This paper investigates the presence of political bias in emotion inference models used for sentiment analysis (SA). Machine learning models often reflect biases in their training data, impacting the validity of their outcomes. While previous research has highlighted gender and race biases,...

Full description

Saved in:
Bibliographic Details
Main Authors: Hubert Plisiecki, Paweł Lenartowicz, Maria Flakus, Artur Pokropek
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-86766-6
Tags: Add Tag
No Tags, Be the first to tag this record!