Elamur Research⌕
☰
home / papers / 2026 / Emotion and Information Disorder in NLP: A Systematic Mapping and Benchmark Blueprint

Emotion and Information Disorder in NLP: A Systematic Mapping and Benchmark Blueprint

Paper · 2026 · Renatha Vieira and Alvaro Figueira

Summary

NLP work on false information increasingly uses affective cues such as sentiment, discrete emotions and emotional trajectories. Most of it still treats the problem as a true/false judgement. That ignores the Information Disorder framework (Wardle and Derakhshan), which separates misinformation, disinformation and mal-information by intent, harm and dependence on context. Vieira and Figueira measure this gap. They built a selective corpus of 82 studies, starting from Semantic Scholar searches and expanding through citation chaining. Each study was coded with a shared scheme covering label types, unit of analysis, emotion representation and use, split strategy and metrics. Among the 58 empirical papers, veracity labels clearly dominate. Intention and harm are almost never annotated directly, and random train/test splits are the norm. Where emotion appears, it is usually a static input feature rather than dynamics or audience reaction. Drawing on these results, the authors put forward a taxonomy designed for practical use, along with a blueprint for building benchmarks. The blueprint treats intent, harm and context as prediction targets and requires source and temporal splits. This gives future datasets a theory-grounded template for comparable evaluation.

Key points

  • Corpus: 82 studies in total, split into 51 model papers, 7 dataset papers and 24 surveys or theory papers. Almost all are in English (80/82).
  • Selection pipeline: 254 retrieved records were narrowed to 60 after title screening and then to a core of 43, before expanding to 82. One author did all screening and coding, with no inter-rater agreement.
  • Label coverage (N=58):
    • 72.4% of empirical studies use binary veracity labels.
    • Explicit intention and harm labels each appear in only 1 study (1.7%).
    • Context dependence is explicit in 17 studies.
  • Evaluation and emotion:
    • 46 of the 58 studies (79.3%) use random splits; only 5 use temporal, 3 cross-domain and 1 cross-lingual splits.
    • Emotion is modelled in 43.1% of model papers.
  • Datasets reviewed: LIAR, FakeNewsNet, Fakeddit, COVID-19 Fake News, Factify 2, PolitiFact-Oslo Corpus and MegaFake. None labels intention explicitly, and harm is at most proxied, in 2 of 7. The blueprint itself remains conceptual and has not yet been validated.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Universidade do PortoPorto · Portugal14 works · 1,992 citations🔬INESC TECPorto · Portugal11 works · 1,180 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksSocial Sciences · 1,772 worksSociology and Political Science · 577 works

🧭 Topics 2Research subjects and languages the work is about.Sentiment & emotion · 972 worksEvaluation & benchmarks · 1,220 works

Cite

Cite as Renatha Vieira and Alvaro Figueira. 2026. Emotion and Information Disorder in NLP: A Systematic Mapping and Benchmark Blueprint. Proceedings of the 1st Workshop on Information Disorder (InDor) @ LREC 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/3xyqihqhsxkj

@inproceedings{vieira2026emotion,
  title = {{Emotion and Information Disorder in NLP: A Systematic Mapping and Benchmark Blueprint}},
  author = {Renatha Vieira and Alvaro Figueira},
  booktitle = {Proceedings of the 1st Workshop on Information Disorder (InDor) @ LREC 2026},
  year = {2026},
  doi = {10.63317/3xyqihqhsxkj},
  url = {https://doi.org/10.63317/3xyqihqhsxkj}
}

References

21 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Haodong Bian and Lisheng Zhang. 2024. Fake news detection incorporating emotion transition in text. Proceedings of the International Conference on Modeling, Natural Language Processing and Machine Learning. find
  2. Bilal Ghanem, Paolo Rosso, and Francisco Rangel. 2019. An emotional analysis of false information in social media and news articles. ACM Transactions on Internet Technology (TOIT), 20:1 – 18. find
  3. Renatha Souza Vieira and Álvaro Figueira. 2025. Emotional sequencing as a marker of manipulation in social media disinformation. Future Internet, 17(12). find
  4. Anastasia Giahanou, Paolo Rosso, and Fabio A. Crestani. 2019. Leveraging emotional signals for credibility detection. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. find
  5. Soroush Vosoughi, Deb K. Roy, and Sinan Aral. 2018. The spread of true and false news online. Science, 359:1146 – 1151. find
  6. Quanjiang Guo, Zhao Kang, Ling Tian, and Zhouguo Chen. 2023. Tiefake: Title-text similarity and emotion-aware fake news detection. 2023 International Joint Conference on Neural Networks (IJCNN), pages 1–7. find
  7. Lionel Z. Wang, Yiming Ma, Renfei Gao, Beichen Guo, Zhuoran Li, Han Zhu, Wenqi Fan, Zexin Lu, and Ka Chung Boris Ng. 2024. Megafake: A theory-driven dataset of fake news generated by large language models. ArXiv, abs/2408.11871. — [arXiv:2408.11871](https://arxiv.org/abs/2408.11871) find
  8. Fei Liu, Xinsheng Zhang, and Qi Liu. 2024. An emotion-aware approach for fake news detection. IEEE Transactions on Computational Social Systems, 11:3516–3524. find
  9. William Yang Wang. 2017. “liar, liar pants on fire”: A new benchmark dataset for fake news detection. In Annual Meeting of the Association for Computational Linguistics.
  10. Kai Nakamura, Sharon Levy, and William Yang Wang. 2020. Fakeddit: A new multimodal benchmark dataset for fine-grained fake news detection. In International Conference on Language Resources and Evaluation. find
  11. Claire Wardle. 2020. Understanding information disorder. First Draft News (long-form article). Accessed 8 June 2025. find
  12. Claire Wardle and Hossein Derakhshan. 2017. Information disorder: Toward an interdisciplinary framework for research and policy making. Technical Report DGI(2017)09, Council of Europe. Council of Europe report, published 27 Sep 2017. find
  13. Parth Patwa, Shivam Sharma, Srinivas Pykl, Vineeth Guptha, Gitanjali Kumari, Md. Shad Akhtar, Asif Ekbal, Amitava Das, and Tanmoy Chakraborty. 2020. Fighting an infodemic: Covid-19 fake news dataset. ArXiv, abs/2011.03327. — [arXiv:2011.03327](https://arxiv.org/abs/2011.03327) find
  14. Liang Wu, Fred Morstatter, Kathleen M. Carley, and Huan Liu. 2019. Misinformation in social media: Definition, manipulation, and detection. SIGKDD Explor., 21:80–90. find
  15. Nele Põldvere, Md. Zia Uddin, and Aleena Thomas. 2023. The politifact-oslo corpus: A new dataset for fake news analysis and detection. Inf., 14:627. find
  16. Xueyao Zhang, Juan Cao, Xirong Li, Qiang Sheng, L. Zhong, and Kai Shu. 2021. Mining dual emotion for fake news detection. Proceedings of the Web Conference 2021. find
  17. Kai Shu, Deepak Mahudeswaran, Suhang Wang, Dongwon Lee, and Huan Liu. 2018. Fakenewsnet: A data repository with news content, social context, and spatiotemporal information for studying fake news on social media. Big Data, 8:171 – 188. find
  18. Xinyi Zhou and Reza Zafarani. 2018. Fake news: A survey of research, detection methods, and opportunities. ArXiv, abs/1812.00315. find
  19. Kai Shu, Amy Lynn Sliva, Suhang Wang, Jiliang Tang, and Huan Liu. 2017. Fake news detection on social media: A data mining perspective. ArXiv, abs/1708.01967. — [arXiv:1708.01967](https://arxiv.org/abs/1708.01967) find
  20. S Suryavardan, Shreyash Mishra, Parth Patwa, Megha Chakraborty, Anku Rani, Aishwarya N. Reganti, Aman Chadha, Amitava Das, Amit P. Sheth, Manoj Kumar Chinnakotla, Asif Ekbal, and Srijan Kumar. 2023. Factify 2: A multimodal fake news and satire news dataset. ArXiv, abs/2304.03897. — [arXiv:2304.03897](https://arxiv.org/abs/2304.03897) find
  21. Lejla Turcilo and Mladen Obrenovic. 2020. Misinformation, disinformation, malinformation: Causes, trends, and their influence on democracy. E-paper series “a companion to democracy”, no. 3, Heinrich Böll Foundation. Publicado em agosto de 2020. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/vieira-2026-emotion-information-disorder-nlp-systematic/