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,...
| Main Authors: | , , |
|---|---|
| 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 |
| _version_ | 1811235255338663936 |
|---|---|
| author | David Rozado Ruth Hughes Jamin Halberstadt |
| author_facet | David Rozado Ruth Hughes Jamin Halberstadt |
| author_sort | David Rozado |
| collection | DOAJ |
| description | 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, disgust, fear, joy, sadness, surprise) plus neutral to automatically label the headlines. Results show an increase of sentiment negativity in headlines across written news media since the year 2000. Headlines from right-leaning news media have been, on average, consistently more negative than headlines from left-leaning outlets over the entire studied time period. The chronological analysis of headlines emotionality shows a growing proportion of headlines denoting anger, fear, disgust and sadness and a decrease in the prevalence of emotionally neutral headlines across the studied outlets over the 2000-2019 interval. The prevalence of headlines denoting anger appears to be higher, on average, in right-leaning news outlets than in left-leaning news media. |
| first_indexed | 2024-04-12T11:48:02Z |
| format | Article |
| id | doaj.art-27f0fe11c7f94d24af26d17344c9d733 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-12T11:48:02Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-27f0fe11c7f94d24af26d17344c9d7332022-12-22T03:34:16ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-011710e027636710.1371/journal.pone.0276367Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models.David RozadoRuth HughesJamin HalberstadtThis 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, disgust, fear, joy, sadness, surprise) plus neutral to automatically label the headlines. Results show an increase of sentiment negativity in headlines across written news media since the year 2000. Headlines from right-leaning news media have been, on average, consistently more negative than headlines from left-leaning outlets over the entire studied time period. The chronological analysis of headlines emotionality shows a growing proportion of headlines denoting anger, fear, disgust and sadness and a decrease in the prevalence of emotionally neutral headlines across the studied outlets over the 2000-2019 interval. The prevalence of headlines denoting anger appears to be higher, on average, in right-leaning news outlets than in left-leaning news media.https://doi.org/10.1371/journal.pone.0276367 |
| spellingShingle | David Rozado Ruth Hughes Jamin Halberstadt Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models. PLoS ONE |
| title | Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models. |
| title_full | Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models. |
| title_fullStr | Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models. |
| title_full_unstemmed | Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models. |
| title_short | Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models. |
| title_sort | longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with transformer language models |
| url | https://doi.org/10.1371/journal.pone.0276367 |
| work_keys_str_mv | AT davidrozado longitudinalanalysisofsentimentandemotioninnewsmediaheadlinesusingautomatedlabellingwithtransformerlanguagemodels AT ruthhughes longitudinalanalysisofsentimentandemotioninnewsmediaheadlinesusingautomatedlabellingwithtransformerlanguagemodels AT jaminhalberstadt longitudinalanalysisofsentimentandemotioninnewsmediaheadlinesusingautomatedlabellingwithtransformerlanguagemodels |