 |
[email protected] |
 |
3275638434 |
 |
 |
| Paper Publishing WeChat |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Yuze Li
Full-Text PDF
XML 50 Views
DOI:10.17265/2159-5836/2026.10.009
Columbia University, New York, USA
This study compares category-to-dimension mapping, a word lexicon, TF-IDF Ridge regression, and contextual RoBERTa regression as computational measures of affective language across valence, arousal, and dominance. Validation against EmoBank and SemEval precedes analysis of within-category variation and application to HuffPost headlines and short descriptions. RoBERTa achieves the strongest benchmark alignment with stable EmoBank rankings across seeds. Emotion categories leave 52.7%–94.4% of model-score variation within labels, and overlapping SemEval annotations reveal human valence variation unexplained by categories. Seven of twelve method-specific trends in the gap between mental-health-related and other health news pass three uncertainty checks; direct contrasts reveal robust method differences only for arousal. Four archival headlines illustrate contrast, negation, recovery-oriented wording, and modality without additional validation. These findings support selecting and validating measures for the affective distinctions a linguistic question requires, focusing on published language rather than audience emotion or population mental health.
affective language, computational measures, mental health news, valence, arousal, dominance, contextual models
Journal of Literature and Art Studies, October 2026, Vol. 16, No. 10, 849-860
Baker, P., Gabrielatos, C., KhosraviNik, M., Krzyżanowski, M., McEnery, T., & Wodak, R. (2008). A useful methodological synergy? Combining critical discourse analysis and corpus linguistics to examine discourses of refugees and asylum seekers in the UK press. Discourse & Society, 19(3), 273-306.
Benjamini, Y., & Hochberg, Y. (1995). Controlling the false discovery rate: A practical and powerful approach to multiple testing. Journal of the Royal Statistical Society: Series B (Methodological), 57(1), 289-300.
Buechel, S., & Hahn, U. (2017). EmoBank: Studying the impact of annotation perspective and representation format on dimensional emotion analysis. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers (pp. 578-585). Association for Computational Linguistics.
Demszky, D., Movshovitz-Attias, D., Ko, J., Cowen, A., Nemade, G., & Ravi, S. (2020). GoEmotions: A dataset of fine-grained emotions. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 4040-4054). Association for Computational Linguistics.
Entman, R. M. (1993). Framing: Toward clarification of a fractured paradigm. Journal of Communication, 43(4), 51-58.
Grimmer, J., & Stewart, B. M. (2013). Text as data: The promise and pitfalls of automatic content analysis methods for political texts. Political Analysis, 21(3), 267-297.
Heegyu. (n.d.). News category dataset [Data set].
Hugging Face. Retrieved from
https://huggingface.co/datasets/heegyu/news-category-dataset/tree/304a05a55bc6abc0446d8fae0d0771716b6a271a
Holmes, L. (2014, January 29). 6 things not to
say to someone with depression. HuffPost. Retrieved from
https://www.huffingtonpost.com/entry/what-not-to-say-to-someon_us_5b9dd1cae4b03a1dcc8d49fd
Jacobs, A. Z., & Wallach, H. (2021). Measurement and fairness. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (pp. 375–385). Association for Computing Machinery.
Kelland, K. (2017, September 7). Treating insomnia can ease depression and paranoia, study finds. HuffPost. Retrieved from https://www.huffingtonpost.com/entry/treating-insomnia-can-ease-depression-and-paranoia-study-finds_us_59b1d8cfe4b0dfaafcf6ccdc
Künsch, H. R. (1989). The jackknife and the bootstrap for general stationary observations. The Annals of Statistics, 17(3), 1217-1241.
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A robustly optimized BERT pretraining approach. arXiv: 1907.11692
MacKinnon, J. G., & White, H. (1985). Some heteroskedasticity-consistent covariance matrix estimators with improved finite sample properties. Journal of Econometrics, 29(3), 305-325
Martin, J. R., & White, P. R. R. (2005). The language of evaluation: Appraisal in English. London: Palgrave Macmillan.
McGinty, E. E., Kennedy-Hendricks, A., Choksy, S., & Barry, C. L. (2016). Trends in news media coverage of mental illness in the United States: 1995-2014. Health Affairs, 35(6), 1121-1129.
Misra, R. (2022). News category dataset. arXiv: 2209.11429
Mohammad, S. M. (2018). Obtaining reliable human ratings of valence, arousal, and dominance for 20,000 English words. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 174-184). Association for Computational Linguistics.
Mohammad, S. M., Bravo-Marquez, F., Salameh, M., & Kiritchenko, S. (2018). SemEval-2018 Task 1: Affect in Tweets. In Proceedings of the 12th International Workshop on Semantic Evaluation (pp. 1-17). Association for Computational Linguistics.
Newey, W. K., & West, K. D. (1987). A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix. Econometrica, 55(3), 703-708.
Park, S., Kim, J., Ye, S., Jeon, J., Park, H. Y., & Oh, A. (2021). Dimensional emotion detection from categorical emotion. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (pp. 4367-4380). Association for Computational Linguistics.
Pervez, A. (2013, June 4). How I overcame depression and became the happy nomad. HuffPost. Retrieved from https://www.huffingtonpost.com/entry/happiness-tips_us_5b9d31d2e4b03a1dcc85633c
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, 17(10), Article e0276367.
Russell, J. A., & Mehrabian, A. (1977). Evidence for a three-factor theory of emotions. Journal of Research in Personality, 11(3), 273-294.
Stuart, H. (2006). Media portrayal of mental illness and its treatments: What effect does it have on people with mental illness? CNS Drugs, 20(2), 99-106.
van der Veen, A. M., & Bleich, E. (2025). The advantages of lexicon-based sentiment analysis in an age of machine learning. PLOS ONE, 20(1), Article e0313092.
Whitley, R., & Campbell, R. D. (2014). Stigma, agency and recovery amongst people with severe mental illness. Social Science & Medicine, 107, 1-8.
Yogis, J. (2012, July 31). Alcohol reduces anxiety but not fear. HuffPost. Retrieved fromhttps://www.huffingtonpost.com/entry/alcohol-effects_us_5b9c0ebee4b03a1dcc7c0dba