---
title: "A Multi-View Framework for Cross-Domain Nutrition"
description: "They build a new expert-labelled collection of English Instagram captions about two contested dietary-fat topics, seed oils and… 24 references."
authors: ["Vishwaa Shah", "Indika Kahanda", "Andrea Arikawa", "Asal Abbaszadeh", "Richard Loftis"]
year: 2026
venue: "BioNLP 2026"
source: "https://aclanthology.org/2026.bionlp-1.26/"
doi: "10.18653/v1/2026.bionlp-1.26"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/shah-2026-multi-view-framework-cross-domain/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shah-2026-multi-view-framework-cross-domain/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/) / A Multi-View Framework for Cross-Domain Nutrition Misinformation Detection in Social Media

# A Multi-View Framework for Cross-Domain Nutrition Misinformation Detection in Social Media

**Authors:** [Vishwaa Shah](https://md.research.elamur.ai/free/en/authors/vishwaa-shah/), [Indika Kahanda](https://md.research.elamur.ai/free/en/authors/indika-kahanda/), [Andrea Arikawa](https://md.research.elamur.ai/free/en/authors/andrea-arikawa/), Asal Abbaszadeh and Richard Loftis · **Year:** 2026 · **Venue:** [BioNLP 2026](https://md.research.elamur.ai/free/en/venues/bionlp/) ([BioNLP 2026](https://md.research.elamur.ai/free/en/venues/bionlp/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.bionlp-1.26/) · [PDF](https://aclanthology.org/2026.bionlp-1.26.pdf) · [DOI 10.18653/v1/2026.bionlp-1.26](https://doi.org/10.18653/v1/2026.bionlp-1.26) · [OpenAlex](https://openalex.org/W7166832091)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Online nutrition misinformation is difficult to catch automatically because it rarely invents facts outright. More often it bends or cherry-picks real scientific findings. The authors address this for Instagram, a platform that has received little attention in misinformation research. They build a new expert-labelled collection of English Instagram captions about two contested dietary-fat topics, seed oils and omega-6. Labels are judged against the 2020–2025 Dietary Guidelines for Americans.

They compare three families of classifiers:
- feature-based models using linguistic complexity, rhetorical/stylistic, and psycholinguistic cues;
- embedding-based models such as Sentence-BERT;
- fine-tuned transformers such as RoBERTa.

Each is tested within one topic and when transferred from one topic to the other. Sentence-BERT performs best in-domain, and an interpretable Random Forest is competitive with it. However, every model loses substantial accuracy in cross-topic transfer, even though the two topics are closely related. The handcrafted psychological and affective features prove more stable under this shift. The work supplies a reusable resource and argues for pairing semantic embeddings with interpretable linguistic signals.

## Key points
- **Dataset and release:** the annotated captions and code are released on Zenodo under CC BY 4.0.
- **Collection setup:**
  - Captions were scraped with Apify Instagram Post Scraper Actors between 28 May and 4 June 2025.
  - Posts date from 2020 onward and come only from accounts with more than 5,000 followers.
  - Searches used fresh accounts (one per topic) and a VPN to reduce personalization bias.
- **In-domain results:** Sentence-BERT achieves the top AUPRC, reaching up to 0.96. RoBERTa favours recall over precision.
- **Cross-domain results:** moving between seed oils and omega-6 causes clear drops, most visibly in AUPRC.
- **Feature analysis:** SHAP on the Random Forest highlights RDoC threat features (acute, potential, sustained threat) and emotion_neutral as the most informative signals. appeal_to_nature also ranks in the top 10. Misinformation tends to show more certainty and less hedging.

*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

- [University of North Florida](https://md.research.elamur.ai/free/en/universities/university-of-north-florida/) — University, Jacksonville, United States · 2 works

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 577 works

## Cite

Cite as: Vishwaa Shah, Indika Kahanda, Andrea Arikawa, Asal Abbaszadeh and Richard Loftis. 2026. A Multi-View Framework for Cross-Domain Nutrition Misinformation Detection in Social Media. BioNLP 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{shah2026multi,
  title = {{A Multi-View Framework for Cross-Domain Nutrition Misinformation Detection in Social Media}},
  author = {Vishwaa Shah, Indika Kahanda, Andrea Arikawa, Asal Abbaszadeh and Richard Loftis},
  booktitle = {BioNLP 2026},
  year = {2026},
  doi = {10.18653/v1/2026.bionlp-1.26},
  url = {https://doi.org/10.18653/v1/2026.bionlp-1.26}
}
```

- [← previous A Multi-Task Learning Framework for Modeling Engagement and Topic-Sensitive Responses in Arabic Women's Discourse](https://md.research.elamur.ai/free/en/papers/bessghaier-2026-multi-task-learning-framework-modeling/)
- [next → A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis](https://md.research.elamur.ai/free/en/papers/manzoor-2026-multi-view-media-profiling-suite/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/)

## References

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

1. Sharique Ahmad, Subuhi Anwar, and Pushpendra D. Pratap. 2025. The cod liver oil insights: From folklore to facts. International Journal of Research -GRANTHAALAYAH, 13(8):95–109. [find](https://scholar.google.com/scholar?q=Sharique+Ahmad%2C+Subuhi+Anwar%2C+and+Pushpendra+D%2E+Pratap%2E+2025%2E+The+cod+liver+oil+insights%3A+From+folklore+to+facts%2E+International+Journal+of+Research+%2DGRANTHAALAYAH%2C+13%288%29%3A95%E2%80%93109%2E)
2. Jamal Belkhouribchia and Joeri Jan Pen. 2025. Large language models in clinical nutrition: an overview of its applications, capabilities, limitations, and potential future prospects. Frontiers in Nutrition, 12:1635682. [find](https://scholar.google.com/scholar?q=Jamal+Belkhouribchia+and+Joeri+Jan+Pen%2E+2025%2E+Large+language+models+in+clinical+nutrition%3A+an+overview+of+its+applications%2C+capabilities%2C+limitations%2C+and+potential+future+prospects%2E+Frontiers+in+Nutr)
3. Brian Dean. 2025. Instagram demographic statistics: How many people use instagram in 2024? Accessed: 2025-04-25. [find](https://scholar.google.com/scholar?q=Brian+Dean%2E+2025%2E+Instagram+demographic+statistics%3A+How+many+people+use+instagram+in+2024%3F+Accessed%3A+2025%2D04%2D25%2E)
4. Connie Diekman, Camille D Ryan, and Tracy L Oliver. 2023. Misinformation and disinformation in food science and nutrition: impact on practice. The Journal of Nutrition, 153(1):3–9. [find](https://scholar.google.com/scholar?q=Connie+Diekman%2C+Camille+D+Ryan%2C+and+Tracy+L+Oliver%2E+2023%2E+Misinformation+and+disinformation+in+food+science+and+nutrition%3A+impact+on+practice%2E+The+Journal+of+Nutrition%2C+153%281%29%3A3%E2%80%939%2E)
5. Dietary Guidelines for Americans. 2020. Dietary guidelines for americans, 2020–2025 and online materials. [https://www.dietaryguidelines.gov/resources/](https://www.dietaryguidelines.gov/resources/) 2020-2025-dietary-guidelines-online-materials. [↗](https://www.dietaryguidelines.gov/resources/)
6. Reyhaneh Farhoundinia, Daniel Munro, and Mark de Rond. 2024. Emotions unveiled: detecting COVID-19 fake news on social media. Humanities and Social Sciences Communications, 11(1):1–14. [find](https://scholar.google.com/scholar?q=Reyhaneh+Farhoundinia%2C+Daniel+Munro%2C+and+Mark+de+Rond%2E+2024%2E+Emotions+unveiled%3A+detecting+COVID%2D19+fake+news+on+social+media%2E+Humanities+and+Social+Sciences+Communications%2C+11%281%29%3A1%E2%80%9314%2E)
7. Cameron Martel, Gordon Pennycook, and David G. Rand. 2020. Reliance on emotion promotes belief in fake news. Cognitive Research: Principles and Implications, 5(1):1–20. [find](https://scholar.google.com/scholar?q=Cameron+Martel%2C+Gordon+Pennycook%2C+and+David+G%2E+Rand%2E+2020%2E+Reliance+on+emotion+promotes+belief+in+fake+news%2E+Cognitive+Research%3A+Principles+and+Implications%2C+5%281%29%3A1%E2%80%9320%2E)
8. Tanjim Bin Faruk. 2024. Evaluating the performance of large language models in scientific claim detection and classification. https://arxiv.org/abs/2412. 16486. [↗](https://arxiv.org/abs/2412)
9. Van Nguyen, Luke Testa, Andrea L Smith, Louise A Ellis, Adam G Dunn, Jeffrey Braithwaite, and Mitchell Sarkies. 2022. Unravelling the truth: Examining the evidence for health-related claims made by naturopathic influencers on social media–a retrospective analysis. Health Promotion Perspectives, 12(4… [find](https://scholar.google.com/scholar?q=Van+Nguyen%2C+Luke+Testa%2C+Andrea+L+Smith%2C+Louise+A+Ellis%2C+Adam+G+Dunn%2C+Jeffrey+Braithwaite%2C+and+Mitchell+Sarkies%2E+2022%2E+Unravelling+the+truth%3A+Examining+the+evidence+for+health%2Drelated+claims+made+by+na)
10. Shubham Garg and Sonal Sharma. 2022. Linguistic features based framework for automatic fake news detection. Computers & Industrial Engineering, 172:108432. [find](https://scholar.google.com/scholar?q=Shubham+Garg+and+Sonal+Sharma%2E+2022%2E+Linguistic+features+based+framework+for+automatic+fake+news+detection%2E+Computers+%26+Industrial+Engineering%2C+172%3A108432%2E)
11. Mohammad Hadi Goldani, Saeedeh Momtazi, and Reza Safabakhsh. 2025. Fighting misinformation in health news: Dcnn-capsnet for cross-domain health misinformation detection. ACM Transactions on Intelligent Systems and Technology. [find](https://scholar.google.com/scholar?q=Mohammad+Hadi+Goldani%2C+Saeedeh+Momtazi%2C+and+Reza+Safabakhsh%2E+2025%2E+Fighting+misinformation+in+health+news%3A+Dcnn%2Dcapsnet+for+cross%2Ddomain+health+misinformation+detection%2E+ACM+Transactions+on+Intelligen)
12. Clayton Hutto and Eric Gilbert. 2014. VADER: A parsimonious rule-based model for sentiment analysis of social media text. In Proceedings of the International AAAI Conference on Web and Social Media, volume 8, pages 216–225. [find](https://scholar.google.com/scholar?q=Clayton+Hutto+and+Eric+Gilbert%2E+2014%2E+VADER%3A+A+parsimonious+rule%2Dbased+model+for+sentiment+analysis+of+social+media+text%2E+In+Proceedings+of+the+International+AAAI+Conference+on+Web+and+Social+Media%2C+v)
13. Thomas R. Insel, Bruce Cuthbert, Marjorie Garvey, Robert Heinssen, Daniel S. Pine, Kevin Quinn, Charles Sanislow, and Philip Wang. 2010. Research domain criteria (rdoc): Toward a new classification framework for research on mental disorders. American Journal of Psychiatry, 167(7):748–756. [find](https://scholar.google.com/scholar?q=Thomas+R%2E+Insel%2C+Bruce+Cuthbert%2C+Marjorie+Garvey%2C+Robert+Heinssen%2C+Daniel+S%2E+Pine%2C+Kevin+Quinn%2C+Charles+Sanislow%2C+and+Philip+Wang%2E+2010%2E+Research+domain+criteria+%28rdoc%29%3A+Toward+a+new+classification+fr)
14. Janne Kauttonen, Jenni Hannukainen, Pia Tikka, and Jyrki Suomala. 2020. Predictive modeling for trustworthiness and other subjective text properties in online nutrition and health communication. PloS one, 15(8):e0237144. [find](https://scholar.google.com/scholar?q=Janne+Kauttonen%2C+Jenni+Hannukainen%2C+Pia+Tikka%2C+and+Jyrki+Suomala%2E+2020%2E+Predictive+modeling+for+trustworthiness+and+other+subjective+text+properties+in+online+nutrition+and+health+communication%2E+PloS+)
15. Jahanzaib Zain Khan, Basheer Alam, and Youngmoon Lee. 2021. An approach utilizing linguistic features for fake news detection. In Proceedings of the 2021 International Conference on Information and Communication Technology Convergence (ICTC), pages 1–6. IEEE. [find](https://scholar.google.com/scholar?q=Jahanzaib+Zain+Khan%2C+Basheer+Alam%2C+and+Youngmoon+Lee%2E+2021%2E+An+approach+utilizing+linguistic+features+for+fake+news+detection%2E+In+Proceedings+of+the+2021+International+Conference+on+Information+and+Co)
16. Kevin Lee and Keszya Kurniawan. 2025. Are seed oils the culprit in cardiometabolic and chronic diseases? a narrative review. Nutrition Reviews, 83(7):e2106– e2112. [find](https://scholar.google.com/scholar?q=Kevin+Lee+and+Keszya+Kurniawan%2E+2025%2E+Are+seed+oils+the+culprit+in+cardiometabolic+and+chronic+diseases%3F+a+narrative+review%2E+Nutrition+Reviews%2C+83%287%29%3Ae2106%E2%80%93+e2112%2E)
17. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv preprint arXiv:1907.11692.
18. Sergio Segado-Fernández, Beatriz Jiménez-Gómez, Pedro Jesús Jiménez-Hidalg, María del Carmen Lozano-Estevan, and Iván Herrera-Peco. 2025. Disinformation about diet and nutrition on social networks: a review of the literature. Nutrición Hospitalaria, 42(2). [find](https://scholar.google.com/scholar?q=Sergio+Segado%2DFern%C3%A1ndez%2C+Beatriz+Jim%C3%A9nez%2DG%C3%B3mez%2C+Pedro+Jes%C3%BAs+Jim%C3%A9nez%2DHidalg%2C+Mar%C3%ADa+del+Carmen+Lozano%2DEstevan%2C+and+Iv%C3%A1n+Herrera%2DPeco%2E+2025%2E+Disinformation+about+diet+and+nutrition+on+social+networks%3A+a+)
19. Wen-Ying Sylvia Chou, Anna Gaysynsky, and Joseph N Cappella. 2020. Where we go from here: health misinformation on social media. [find](https://scholar.google.com/scholar?q=Wen%2DYing+Sylvia+Chou%2C+Anna+Gaysynsky%2C+and+Joseph+N+Cappella%2E+2020%2E+Where+we+go+from+here%3A+health+misinformation+on+social+media%2E)
20. Dongmei Tan, Yi Huang, Ming Liu, Ziyu Li, Xiaoqian Wu, and Cheng Huang. 2025. Identification of online health information using large pretrained language models: Mixed methods study. Journal of Medical Internet Research, 27:e70733. [find](https://scholar.google.com/scholar?q=Dongmei+Tan%2C+Yi+Huang%2C+Ming+Liu%2C+Ziyu+Li%2C+Xiaoqian+Wu%2C+and+Cheng+Huang%2E+2025%2E+Identification+of+online+health+information+using+large+pretrained+language+models%3A+Mixed+methods+study%2E+Journal+of+Medica)
21. Pawan Kumar Verma, Priyanka Agrawal, Isabelle Amorim, and Radu Prodan. 2021. WELFake: Word embedding over linguistic features for fake news detection. IEEE Transactions on Computational Social Systems, 8(4):881–893. [find](https://scholar.google.com/scholar?q=Pawan+Kumar+Verma%2C+Priyanka+Agrawal%2C+Isabelle+Amorim%2C+and+Radu+Prodan%2E+2021%2E+WELFake%3A+Word+embedding+over+linguistic+features+for+fake+news+detection%2E+IEEE+Transactions+on+Computational+Social+Systems)
22. Christiane Wurst, Paul Sauseng, Shruthi Prasad, Anchali Trakulp, Cameron Martel, and David Rand. 2024. Emotions in misinformation studies: distinguishing affective state from emotional response and misinformation recognition from acceptance. Cognitive Research: Principles and Implications, 9(1):1–18… [find](https://scholar.google.com/scholar?q=Christiane+Wurst%2C+Paul+Sauseng%2C+Shruthi+Prasad%2C+Anchali+Trakulp%2C+Cameron+Martel%2C+and+David+Rand%2E+2024%2E+Emotions+in+misinformation+studies%3A+distinguishing+affective+state+from+emotional+response+and+mi)
23. Constantinos-Giovanni Xarhoulacos, Argiro Anagnostopoulou, George Stergiopoulos, and Dimitris Gritzalis. 2021. Misinformation vs. situational awareness: The art of deception and the need for cross-domain detection. Sensors, 21(16):5496. [find](https://scholar.google.com/scholar?q=Constantinos%2DGiovanni+Xarhoulacos%2C+Argiro+Anagnostopoulou%2C+George+Stergiopoulos%2C+and+Dimitris+Gritzalis%2E+2021%2E+Misinformation+vs%2E+situational+awareness%3A+The+art+of+deception+and+the+need+for+cross%2Ddom)
24. Andy Wai Kan Yeung, Anela Tosevska, Elisabeth Klager, Fabian Eibensteiner, Christos Tsagkaris, Emil D Parvanov, Faisal A Nawaz, Sabine Völkl-Kernstock, Eva Schaden, Maria Kletecka-Pulker, and 1 others. 2022. Medical and health-related misinformation on social media: bibliometric study of the scienti… [find](https://scholar.google.com/scholar?q=Andy+Wai+Kan+Yeung%2C+Anela+Tosevska%2C+Elisabeth+Klager%2C+Fabian+Eibensteiner%2C+Christos+Tsagkaris%2C+Emil+D+Parvanov%2C+Faisal+A+Nawaz%2C+Sabine+V%C3%B6lkl%2DKernstock%2C+Eva+Schaden%2C+Maria+Kletecka%2DPulker%2C+and+1+others)

*Updated 1 November 2026*