Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models.

Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models.

Show other versions (1)

This work describes a chronological (2000-2019) analysis of sentiment and emotion in 23 million headlines from 47 news media outlets popular in the United States. We use Transformer language models fine-tuned for detection of sentiment (positive, negative) and Ekman's six basic emotions (anger,...

Full description

Bibliographic Details
Main Authors: David Rozado, Ruth Hughes, Jamin Halberstadt
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2022-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0276367

Similar Items

Similar Items