Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
An argument for basic emotions
Ekman, P. (1992) · Cognition and Emotion · doi:10.1080/02699939208411068 · Cited by 9,646 · cited 1×
“We used a public Transformer DistilRoBERTa-base checkpoint previously fine-tuned on 6 different emotion data sets for recognizing Ekman’s 6 basic emotions (anger, disgust, fear, joy, sadness, and surprise) plus neutral [28, 30, 31].”
MethodThe Content Analysis Guidebook
Neuendorf, K. A. (2017) · doi:10.4135/9781071802878 · Cited by 9,286
What Makes Online Content Viral?
Berger, J., & Milkman, K. L. (2012) · Journal of Marketing Research · doi:10.1509/jmr.10.0353 · Cited by 3,178 · cited 1×
“Textual content that evokes high arousal, such as text conveying an emotion of anger, diffuses more profusely through online platforms [5, 6].”
BackgroundContextual prerequisites for understanding: Some investigations of comprehension and recall
Bransford, J. D., & Johnson, M. K. (1972) · Journal of Verbal Learning and Verbal Behavior · doi:10.1016/s0022-5371(72)80006-9 · Cited by 2,131
Emotion shapes the diffusion of moralized content in social networks
Brady, W. J., Wills, J. A., Jost, J. T., Tucker, J. A., & Van Bavel, J. J. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1618923114 · Cited by 1,580 · cited 1×
“A study measuring the reach of tweets found that each moral or emotional word used in a tweet increased its virality by 20 percent, on average [8].”
BackgroundOut-group animosity drives engagement on social media
Rathje, S., Van Bavel, J. J., & van der Linden, S. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2024292118 · Cited by 560
Good Friends, Bad News - Affect and Virality in Twitter
Hansen, L. K., Arvidsson, A., Nielsen, F. A., Colleoni, E., & Etter, M. (2011) · Communications in Computer and Information Science · doi:10.1007/978-3-642-22309-9_5 · Cited by 361
More than a Feeling: Accuracy and Application of Sentiment Analysis
Hartmann, J., Heitmann, M., Siebert, C., & Schamp, C. (2023) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2022.05.005 · Cited by 356 · cited 1×
“In this work we use SiEBERT, a public checkpoint of a RoBERTa-large Transformer architecture [26] previously fine-tuned and evaluated for sentiment analysis on 15 data sets from diverse text sources to enhance generalization of sentiment annotations across different types of text [27].”
Method
Cited by
Algorithm-mediated social learning in online social networks
Brady, W. J., Jackson, J. C., Lindström, B., & Crockett, M. J. (2023) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2023.06.008 · Cited by 132
Ittefaq, M., Zain, A., Arif, R., Ala-Uddin, M., Ahmad, T., & Iqbal, A. (2025) · Telematics and Informatics · doi:10.1016/j.tele.2024.102223 · Cited by 82
Negative online news articles are shared more to social media
Watson, J., van der Linden, S., Watson, M., & Stillwell, D. (2024) · Scientific Reports · doi:10.1038/s41598-024-71263-z · Cited by 70
Pan, S., Xu, G. J. W., Guo, K., Park, S. H., & Ding, H. (2024) · IEEE Transactions on Games · doi:10.1109/tg.2024.3366239 · Cited by 38
“These models are capable of predicting six basic emotions proposed by Ekman [59] (anger, disgust, fear, joy, sadness, and surprise), as well as a neutral emotion, from text and have been successfully applied in other studies related to text analysis [60], [61].”
Emotionally based strategic communications as a new tool in defensive cognitive warfare
Ćosić, K., Popović, S., & Wiederhold, B. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1751406 · Cited by 4
Metadata
- Authors
- Rozado, D., Hughes, R., & Halberstadt, J.
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2022-10-18
- Volume
- 17
- Issue
- 10
- Pages
- e0276367
- ISSN
- 1932-6203 (ISSN-L)
- OpenAlex
- W4306732251
- Cited by
- 103
- References
- 10
- FWCI
- 6.46
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models. https://app.cochat.ai/papers/10.1371/journal.pone.0276367
- The paper
- Rozado, D., Hughes, R., & Halberstadt, J. (2022). Longitudinal analysis of sentiment and emotion in news media headlines using automated labelling with Transformer language models. PLOS ONE. https://doi.org/10.1371/journal.pone.0276367
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.