From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media

Elisavet Andrikopoulou; Michael Rigby; Kathrin Cresswell; Aikaterini Kanta; Jordi Piera-Jiménez

doi:10.3233/SHTI260785

From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media

Elisavet Andrikopoulou^*
, Michael Rigby
, Kathrin Cresswell
, Aikaterini Kanta
, Jordi Piera-Jiménez

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

13 Downloads (Pure)

Abstract

Large Language Models (LLMs) are increasingly used to appraise health claims on social media (SM) platforms such as TikTok, yet no consistent approach
exists for evaluating how they judge clinical accuracy or misleadingness. This
narrative review develops a conceptual understanding of how LLMs should be
evaluated as health information mediators in SM environments, using TikTok as a use case. We searched Google Scholar for peer-reviewed journal articles and
conference papers, published between January 2022 and January 2026. Findings
indicate that LLM outputs may be perceived as authoritative even when clinical
accuracy is not independently verified. Identified evaluation approaches include
reference-standard alignment, safety stress testing, knowledge-augmented
verification, and prompt robustness testing. TikTok-focused studies highlight
platform-specific risks, where entertainment-driven formats and influencer
credibility can amplify misleading claims. Overall, robust evaluation requires four dimensions: alignment with clinical guidelines, prompt robustness, harm resistance, and sensitivity to platform-specific affordances such as short-form and multimodal content.

Original language	English
Title of host publication	Health Sciences Informatics Leads and Empowers the Digital Health Transformation
Editors	John Mantas, Arie Hasman, Parisis Gallos, Reinhold Haux, Konstantinos Karitis
Publisher	IOS Press
Pages	6-10
ISBN (Electronic)	9781643686684
DOIs	https://doi.org/10.3233/SHTI260785
Publication status	Published - 2 Jul 2026
Event	24th International Conference on Informatics, Management and Technology in Healthcare: ICIMTH 2026 - Athens, Greece Duration: 3 Jul 2026 → 5 Jul 2026

Publication series

Name	Studies in Health Technology and Informatics
Volume	338
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Conference

Conference	24th International Conference on Informatics, Management and Technology in Healthcare
Country/Territory	Greece
City	Athens
Period	3/07/26 → 5/07/26

Keywords

LLM
Health misinformation
social media
TikTok
clinical accuracy
evaluation frameworks
digital health communication

Access to Document

10.3233/SHTI260785

SHTI-338-SHTI260785Final published version, 202 KBLicence: CC BY-NC

Cite this

Andrikopoulou, E., Rigby, M., Cresswell, K., Kanta, A., & Piera-Jiménez, J. (2026). From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media. In J. Mantas, A. Hasman, P. Gallos, R. Haux, & K. Karitis (Eds.), Health Sciences Informatics Leads and Empowers the Digital Health Transformation (pp. 6-10). (Studies in Health Technology and Informatics; Vol. 338). IOS Press. https://doi.org/10.3233/SHTI260785

Andrikopoulou, Elisavet ; Rigby, Michael ; Cresswell, Kathrin et al. / From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media. Health Sciences Informatics Leads and Empowers the Digital Health Transformation. editor / John Mantas ; Arie Hasman ; Parisis Gallos ; Reinhold Haux ; Konstantinos Karitis. IOS Press, 2026. pp. 6-10 (Studies in Health Technology and Informatics).

@inproceedings{ceab57a859054b23b862646934bdc752,

title = "From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media",

abstract = "Large Language Models (LLMs) are increasingly used to appraise health claims on social media (SM) platforms such as TikTok, yet no consistent approach exists for evaluating how they judge clinical accuracy or misleadingness. This narrative review develops a conceptual understanding of how LLMs should be evaluated as health information mediators in SM environments, using TikTok as a use case. We searched Google Scholar for peer-reviewed journal articles and conference papers, published between January 2022 and January 2026. Findings indicate that LLM outputs may be perceived as authoritative even when clinical accuracy is not independently verified. Identified evaluation approaches include reference-standard alignment, safety stress testing, knowledge-augmented verification, and prompt robustness testing. TikTok-focused studies highlight platform-specific risks, where entertainment-driven formats and influencer credibility can amplify misleading claims. Overall, robust evaluation requires four dimensions: alignment with clinical guidelines, prompt robustness, harm resistance, and sensitivity to platform-specific affordances such as short-form and multimodal content. ",

keywords = "LLM, Health misinformation, social media, TikTok, clinical accuracy, evaluation frameworks, digital health communication",

author = "Elisavet Andrikopoulou and Michael Rigby and Kathrin Cresswell and Aikaterini Kanta and Jordi Piera-Jim{\'e}nez",

year = "2026",

month = jul,

day = "2",

doi = "10.3233/SHTI260785",

language = "English",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "6--10",

editor = "John Mantas and Arie Hasman and Parisis Gallos and Reinhold Haux and Konstantinos Karitis",

booktitle = "Health Sciences Informatics Leads and Empowers the Digital Health Transformation",

address = "Netherlands",

note = "24th International Conference on Informatics, Management and Technology in Healthcare : ICIMTH 2026 ; Conference date: 03-07-2026 Through 05-07-2026",

}

Andrikopoulou, E, Rigby, M, Cresswell, K, Kanta, A & Piera-Jiménez, J 2026, From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media. in J Mantas, A Hasman, P Gallos, R Haux & K Karitis (eds), Health Sciences Informatics Leads and Empowers the Digital Health Transformation. Studies in Health Technology and Informatics, vol. 338, IOS Press, pp. 6-10, 24th International Conference on Informatics, Management and Technology in Healthcare, Athens, Greece, 3/07/26. https://doi.org/10.3233/SHTI260785

From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media. / Andrikopoulou, Elisavet; Rigby, Michael; Cresswell, Kathrin et al.
Health Sciences Informatics Leads and Empowers the Digital Health Transformation. ed. / John Mantas; Arie Hasman; Parisis Gallos; Reinhold Haux; Konstantinos Karitis. IOS Press, 2026. p. 6-10 (Studies in Health Technology and Informatics; Vol. 338).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media

AU - Andrikopoulou, Elisavet

AU - Rigby, Michael

AU - Cresswell, Kathrin

AU - Kanta, Aikaterini

AU - Piera-Jiménez, Jordi

PY - 2026/7/2

Y1 - 2026/7/2

N2 - Large Language Models (LLMs) are increasingly used to appraise health claims on social media (SM) platforms such as TikTok, yet no consistent approach exists for evaluating how they judge clinical accuracy or misleadingness. This narrative review develops a conceptual understanding of how LLMs should be evaluated as health information mediators in SM environments, using TikTok as a use case. We searched Google Scholar for peer-reviewed journal articles and conference papers, published between January 2022 and January 2026. Findings indicate that LLM outputs may be perceived as authoritative even when clinical accuracy is not independently verified. Identified evaluation approaches include reference-standard alignment, safety stress testing, knowledge-augmented verification, and prompt robustness testing. TikTok-focused studies highlight platform-specific risks, where entertainment-driven formats and influencer credibility can amplify misleading claims. Overall, robust evaluation requires four dimensions: alignment with clinical guidelines, prompt robustness, harm resistance, and sensitivity to platform-specific affordances such as short-form and multimodal content.

AB - Large Language Models (LLMs) are increasingly used to appraise health claims on social media (SM) platforms such as TikTok, yet no consistent approach exists for evaluating how they judge clinical accuracy or misleadingness. This narrative review develops a conceptual understanding of how LLMs should be evaluated as health information mediators in SM environments, using TikTok as a use case. We searched Google Scholar for peer-reviewed journal articles and conference papers, published between January 2022 and January 2026. Findings indicate that LLM outputs may be perceived as authoritative even when clinical accuracy is not independently verified. Identified evaluation approaches include reference-standard alignment, safety stress testing, knowledge-augmented verification, and prompt robustness testing. TikTok-focused studies highlight platform-specific risks, where entertainment-driven formats and influencer credibility can amplify misleading claims. Overall, robust evaluation requires four dimensions: alignment with clinical guidelines, prompt robustness, harm resistance, and sensitivity to platform-specific affordances such as short-form and multimodal content.

KW - LLM

KW - Health misinformation

KW - social media

KW - TikTok

KW - clinical accuracy

KW - evaluation frameworks

KW - digital health communication

U2 - 10.3233/SHTI260785

DO - 10.3233/SHTI260785

M3 - Conference contribution

T3 - Studies in Health Technology and Informatics

SP - 6

EP - 10

BT - Health Sciences Informatics Leads and Empowers the Digital Health Transformation

A2 - Mantas, John

A2 - Hasman, Arie

A2 - Gallos, Parisis

A2 - Haux, Reinhold

A2 - Karitis, Konstantinos

PB - IOS Press

T2 - 24th International Conference on Informatics, Management and Technology in Healthcare

Y2 - 3 July 2026 through 5 July 2026

ER -

Andrikopoulou E, Rigby M, Cresswell K, Kanta A, Piera-Jiménez J. From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media. In Mantas J, Hasman A, Gallos P, Haux R, Karitis K, editors, Health Sciences Informatics Leads and Empowers the Digital Health Transformation. IOS Press. 2026. p. 6-10. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI260785

From Chatbots to MythTok: a narrative review of LLMs as health information mediators on social media

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this