Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models
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, disg...
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://www.ncbi.nlm.nih.gov/pmc/articles/PMC9578611/?tool=EBI |
Similar Items
-
Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models.
by: David Rozado, et al.
Published: (2022-01-01) -
A Sesotho news headlines dataset for sentiment analysis
by: Refuoe Mokhosi, et al.
Published: (2024-06-01) -
Structure of Headline Complex in News Media Discourse
by: A. V. Sineleva
Published: (2019-06-01) -
Fake news reminders and veracity labels differentially benefit memory and belief accuracy for news headlines
by: Paige L. Kemp, et al.
Published: (2022-12-01) -
TRANSITION SIGNALS IN HEADLINE NEWS
by: Indah Sari
Published: (2022-12-01)